Daily Papers

Domain models are central to software engineering, as they enable a shared understanding, guide implementation, and support automated analyses and model-driven development. Yet, despite these benefits, practitioners often skip modeling because it is time-consuming and demands scarce expertise. We address this barrier by investigating whether open-weight large language models, adapted via instruction tuning, can generate high-quality BPMN process models directly from natural language descriptions in a cost-effective and privacy-preserving way. We introduce InstruBPM, a reproducible approach that prepares paired text-diagram data and instruction tunes an open source large language model with parameter-efficient fine-tuning and quantization for on-prem deployment. We evaluate the tuned model through complementary perspectives: (i) text/code similarity using BLEU, ROUGE-L, and METEOR, (ii) structural fidelity using Relative Graph Edit Distance, (iii) guidelines conformance using external tool checks, and (iv) a small expert review. Using a curated subset of a multi-domain BPMN dataset, we compare the tuned model with untuned open-weight baselines and strong proprietary models under consistent prompting regimes. Our compact tuned model outperforms all baselines across sequence and structural metrics while requiring substantially fewer resources; guideline analysis and expert feedback further indicate that the generated diagrams largely follow BPMN best practices and are useful starting points that reduce modeling effort. Overall, instruction tuning improves structural accuracy and robustness compared to untuned baselines and reduces reliance on heavy prompt scaffolding. We publicly share the trained models and scripts to support reproducibility and further research.

Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) have memorized plaintiffs' protected expression in their training data. Drawing on both machine learning and copyright law, we show that these polarized positions dramatically oversimplify the relationship between memorization and copyright. To do so, we extend a recent probabilistic extraction technique to measure memorization of 50 books in 17 open-weight LLMs. Through thousands of experiments, we show that the extent of memorization varies both by model and by book. With respect to our specific extraction methodology, we find that most LLMs do not memorize most books -- either in whole or in part. However, we also find that Llama 3.1 70B entirely memorizes some books, like the first Harry Potter book and 1984. In fact, the first Harry Potter is so memorized that, using a seed prompt consisting of just the first few tokens of the first chapter, we can deterministically generate the entire book near-verbatim. We discuss why our results have significant implications for copyright cases, though not ones that unambiguously favor either side.

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largely focused on input-based jailbreaking and parameter-level manipulations. However, open-weight models also natively support prefilling, which allows an attacker to predefine initial response tokens before generation begins. Despite its potential, this attack vector has received little systematic attention. We present the largest empirical study to date of prefill attacks, evaluating over 20 existing and novel strategies across multiple model families and state-of-the-art open-weight models. Our results show that prefill attacks are consistently effective against all major contemporary open-weight models, revealing a critical and previously underexplored vulnerability with significant implications for deployment. While certain large reasoning models exhibit some robustness against generic prefilling, they remain vulnerable to tailored, model-specific strategies. Our findings underscore the urgent need for model developers to prioritize defenses against prefill attacks in open-weight LLMs.

Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that validate users rather than prioritize factual accuracy. While prior work has established that sycophancy poses risks to AI safety and alignment, the relationship between specific personality traits of adopted personas and the degree of sycophantic behavior remains unexplored. We present a systematic investigation of how persona agreeableness influences sycophancy across 13 small, open-weight language models ranging from 0.6B to 20B parameters. We develop a benchmark comprising 275 personas evaluated on NEO-IPIP agreeableness subscales and expose each persona to 4,950 sycophancy-eliciting prompts spanning 33 topic categories. Our analysis reveals that 9 of 13 models exhibit statistically significant positive correlations between persona agreeableness and sycophancy rates, with Pearson correlations reaching r = 0.87 and effect sizes as large as Cohen's d = 2.33. These findings demonstrate that agreeableness functions as a reliable predictor of persona-induced sycophancy, with direct implications for the deployment of role-playing AI systems and the development of alignment strategies that account for personality-mediated deceptive behaviors.

Leading large language models have demonstrated impressive capabilities in reasoning-intensive tasks, such as standardized educational testing. However, they often require extensive training in low-resource settings with inaccessible infrastructure. Small or compact models, though more efficient, frequently lack sufficient support for underrepresented languages, leaving a performance gap in critical domains. This work explores the potential of parameter-efficient fine-tuning of compact open-weight language models to handle reasoning-intensive tasks in the underrepresented Ukrainian language, building on the findings of the ZNO-Eval benchmark. Parameter-efficient fine-tuning of LLaMA 3.1 (8 billion parameters), LLaMA 3.2 (3 billion parameters), and Gemma 2 (9 billion parameters) models on chain-of-thought solutions resulted in a modest test score improvement of up to 17.4% on complex matching tasks and 1.6% overall compared to tuning on answer letters alone, offering enhanced interpretability and robustness. In addition, the proposed tuning method with joint task topic and step-by-step solution generation outperforms standard chain-of-thought tuning in matching tasks and provides a 5.4% gain over the best LLaMA 3.2 model due to guiding the model to recall and apply domain-relevant information. Contrasting obtained results with zero-shot evaluations of leading open-weight and proprietary models such as Qwen, DeepSeek R1, OpenAI o1 and o3, Gemini, and Claude, highlight that fine-tuning LLaMA and Gemma models with 2,032 step-by-step solutions and 20 to 50 million trainable parameters on a single A100 GPU lets them outperform GPT-4o mini, Mistral Large, and larger open-weight models. This research also evaluates how merging the quantized adapter with the base model influences the generation quality. Source code and tuned models are available at https://github.com/NLPForUA/ZNO.

Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more reliable for such decisions, and interventions to design higher-quality evaluation benchmarks. We introduce two key metrics that show differences in current benchmarks: signal, a benchmark's ability to separate better models from worse models, and noise, a benchmark's sensitivity to random variability between training steps. We demonstrate that benchmarks with a better signal-to-noise ratio are more reliable when making decisions at small scale, and those with less noise have lower scaling law prediction error. These results suggest that improving signal or noise will lead to more useful benchmarks, so we introduce three interventions designed to directly affect signal or noise. For example, we propose that switching to a metric that has better signal and noise (e.g., perplexity rather than accuracy) leads to better reliability and improved scaling law error. We also find that filtering noisy subtasks, to improve an aggregate signal-to-noise ratio, leads to more reliable multi-task evaluations. We also find that averaging the output of a model's intermediate checkpoints to reduce noise leads to consistent improvements. We conclude by recommending that those creating new benchmarks, or selecting which existing benchmarks to use, aim for high signal and low noise. We use 30 benchmarks for these experiments, and 375 open-weight language models from 60M to 32B parameters, resulting in a new, publicly available dataset of 900K evaluation benchmark results, totaling 200M instances.

We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architecture. The transformation is performed by Efficient Knowledge Preservation for Transformation (KEPT), a recipe that combines (i) Normal Parameter Mapping (NPM) for unchanged modules, (ii) Optimized Parameter Mapping (OPM), a training-free LayerNorm-to-RMSNorm initialization we prove optimal under the near-zero-mean activation regime induced by weight decay, and (iii) Cross-architecture Knowledge Distillation (XKD), an equal-size frozen-teacher distillation that aligns the converted model's outputs with the source model's on any reasonable input distribution. Llamion recovers Orion's behaviour on H6, MT-Bench, and KoMMLU with only ~123M tokens on a single A100 in four days; Llamion-Base reaches 66.87% on KoMMLU, exceeding the next-best entry of the Open Ko LLM Leaderboard by >7.0 absolute points at submission time. Capabilities entirely absent from the transfer corpus (Python programming and 200K-token context handling) survive the architectural transition intact. We release three checkpoints (Base, Chat, LongChat) that load with trust_remote_code=False in the Hugging Face Transformers library.

Mathematics has long been conveyed through natural language, primarily for human understanding. With the rise of mechanized mathematics and proof assistants, there is a growing need to understand informal mathematical text, yet most existing benchmarks focus solely on English, overlooking other languages. This paper introduces RoMath, a Romanian mathematical reasoning benchmark suite comprising three datasets: RoMath-Baccalaureate, RoMath-Competitions and RoMath-Synthetic, which cover a range of mathematical domains and difficulty levels, aiming to improve non-English language models and promote multilingual AI development. By focusing on Romanian, a low-resource language with unique linguistic features, RoMath addresses the limitations of Anglo-centric models and emphasizes the need for dedicated resources beyond simple automatic translation. We benchmark several open-weight language models, highlighting the importance of creating resources for underrepresented languages. We make the code and dataset available.

Scientific progress depends on sequences of enabling contributions, yet existing AI4Science benchmarks largely focus on citation prediction, literature retrieval, or idea generation rather than the dependencies that make progress possible. In this paper, we introduce discovery pathway forecasting: given a target scientific contribution and the prior literature available at a specified time, the task is to (1) identify the enabling contributions required to realize it and (2) ground each in prior work when such prior work exists. We present SciPaths, a benchmark of 262 expert-annotated gold pathways and 2,444 silver pathways constructed from machine learning and natural language processing papers, where each pathway records enabling contributions, roles, rationales, and prior-work groundings or unmapped decisions. Evaluating frontier and open-weight language models, we find that the best model reaches only 0.189 F1 under strict semantic matching, with core methodological dependencies hardest to recover. Prior-work grounding improves substantially when gold enabling contributions are provided, showing that decomposition quality is a major bottleneck for end-to-end pathway recovery. SciPaths therefore shifts evaluation toward a missing capability in scientific forecasting: reasoning backward from a target contribution to the enabling scientific building blocks and prior-work dependencies that make it feasible.

Despite progress in Arabic large language models, such as Jais and AceGPT, their evaluation on commonsense reasoning has largely relied on machine-translated datasets, which lack cultural depth and may introduce Anglocentric biases. Commonsense reasoning is shaped by geographical and cultural contexts, and existing English datasets fail to capture the diversity of the Arab world. To address this, we introduce \datasetname, a commonsense reasoning dataset in Modern Standard Arabic (MSA), covering cultures of 13 countries across the Gulf, Levant, North Africa, and the Nile Valley. The dataset was built from scratch by engaging native speakers to write and validate culturally relevant questions for their respective countries. \datasetname spans 12 daily life domains with 54 fine-grained subtopics, reflecting various aspects of social norms, traditions, and everyday experiences. Zero-shot evaluations show that open-weight language models with up to 32B parameters struggle to comprehend diverse Arab cultures, with performance varying across regions. These findings highlight the need for more culturally aware models and datasets tailored to the Arabic-speaking world.

Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across individuals and contexts -- a phenomenon established in behavioral economics and discrete choice theory. This mismatch limits the ability of existing objectives to faithfully capture heterogeneous human judgments. Inspired by this literature, we introduce Mixed Logit Direct Preference Optimization (MixDPO), a generalization of Direct Preference Optimization that models variation in preference strength. MixDPO enables alignment objectives to capture heterogeneity in how strongly preferences are expressed across training examples. We evaluate MixDPO on three preference datasets using two open-weight language models. Across datasets, MixDPO improves aggregate alignment performance (+11.2 points on Pythia-2.8B) while preserving subgroup level preferences, with the largest gains appearing in settings with higher inferred preference heterogeneity. MixDPO makes preference heterogeneity explicit through learned strength distributions. We release our code for reproducibility.

Many recent works have explored using language models for planning problems. One line of research focuses on translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition language (PDDL). While this approach is promising, accurately measuring the quality of generated PDDL code continues to pose significant challenges. First, generated PDDL code is typically evaluated using planning validators that check whether the problem can be solved with a planner. This method is insufficient because a language model might generate valid PDDL code that does not align with the natural language description of the task. Second, existing evaluation sets often have natural language descriptions of the planning task that closely resemble the ground truth PDDL, reducing the challenge of the task. To bridge this gap, we introduce \benchmarkName, a benchmark designed to evaluate language models' ability to generate PDDL code from natural language descriptions of planning tasks. We begin by creating a PDDL equivalence algorithm that rigorously evaluates the correctness of PDDL code generated by language models by flexibly comparing it against a ground truth PDDL. Then, we present a dataset of 132,037 text-to-PDDL pairs across 13 different tasks, with varying levels of difficulty. Finally, we evaluate several API-access and open-weight language models that reveal this task's complexity. For example, 87.6% of the PDDL problem descriptions generated by GPT-4o are syntactically parseable, 82.2% are valid, solve-able problems, but only 35.1% are semantically correct, highlighting the need for a more rigorous benchmark for this problem.

Despite initial successes and a variety of architectures, retrieval-augmented generation (RAG) systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG frameworks regard all retrieved information as equally reliable, overlooking the varying credibility and interconnected nature of large textual corpora. GraphRAG approaches offer potential improvement to RAG systems by integrating knowledge graphs, which structure information into nodes and edges, capture entity relationships, and enable multi-step logical traversal. However, GraphRAG is not always an ideal solution as it depends on high-quality graph representations of the corpus, which requires either pre-existing knowledge graphs that are expensive to build and update, or automated graph construction pipelines that are often unreliable. Moreover, systems following this paradigm typically use large language models to guide graph traversal and evidence retrieval, leading to challenges similar to those encountered with standard RAG. In this paper, we propose a novel RAG framework that employs the spreading activation algorithm to retrieve information from a corpus of documents interconnected by automatically constructed knowledge graphs, thereby enhancing the performance of large language models on complex tasks such as multi-hop question answering. Experiments show that our method achieves better or comparable performance to iterative RAG methodologies, while also being easily integrable as a plug-and-play module with a wide range of RAG-based approaches. Combining our method with chain-of-thought iterative retrieval yields up to a 39\% absolute gain in answer correctness compared to naive RAG, achieving these results with small open-weight language models and highlighting its effectiveness in resource-constrained settings.

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction approach can be easily adapted to other languages; we build datasets for Japanese and confirm that LLMs tuned with our data reach state-of-the-art performance. Analyses suggest that instruction-tuning in a new language allows LLMs to follow instructions, while the tuned models exhibit a notable lack of culture-specific knowledge in that language. The datasets and fine-tuned models will be publicly available. Our datasets, synthesized with open-weight LLMs, are openly distributed under permissive licenses, allowing for diverse use cases.

Background: Reporting and Data Systems (RADS) standardize radiology risk communication but automated RADS assignment from narrative reports is challenging because of guideline complexity, output-format constraints, and limited benchmarking across RADS frameworks and model sizes. Purpose: To create RXL-RADSet, a radiologist-verified synthetic multi-RADS benchmark, and compare validity and accuracy of open-weight small language models (SLMs) with a proprietary model for RADS assignment. Materials and Methods: RXL-RADSet contains 1,600 synthetic radiology reports across 10 RADS (BI-RADS, CAD-RADS, GB-RADS, LI-RADS, Lung-RADS, NI-RADS, O-RADS, PI-RADS, TI-RADS, VI-RADS) and multiple modalities. Reports were generated by LLMs using scenario plans and simulated radiologist styles and underwent two-stage radiologist verification. We evaluated 41 quantized SLMs (12 families, 0.135-32B parameters) and GPT-5.2 under a fixed guided prompt. Primary endpoints were validity and accuracy; a secondary analysis compared guided versus zero-shot prompting. Results: Under guided prompting GPT-5.2 achieved 99.8% validity and 81.1% accuracy (1,600 predictions). Pooled SLMs (65,600 predictions) achieved 96.8% validity and 61.1% accuracy; top SLMs in the 20-32B range reached ~99% validity and mid-to-high 70% accuracy. Performance scaled with model size (inflection between <1B and >=10B) and declined with RADS complexity primarily due to classification difficulty rather than invalid outputs. Guided prompting improved validity (99.2% vs 96.7%) and accuracy (78.5% vs 69.6%) compared with zero-shot. Conclusion: RXL-RADSet provides a radiologist-verified multi-RADS benchmark; large SLMs (20-32B) can approach proprietary-model performance under guided prompting, but gaps remain for higher-complexity schemes.

We demonstrate that the inference operations of several open-weight large language models (LLMs) can be mapped to an exactly equivalent linear system for an input sequence without modifying the model weights or altering output predictions. Extending techniques from image diffusion models that exhibit local or piecewise linearity, we strategically alter the gradient computation with respect to a given input sequence for a next-token prediction such that the Jacobian of the model nearly exactly reproduces the forward prediction with a linear system. We demonstrate this approach across models (Llama 3, Gemma 3, Qwen 3, Phi 4, Mistral Ministral and OLMo 2, up to Llama 3.3 70B Q4) and show through the singular value decomposition of the detached Jacobian that these LLMs operate in extremely low-dimensional subspaces where many of the largest singular vectors decode to concepts related to the most-likely output token. This approach also allows us to examine the operation of each successive layer (and its attention and MLP components) as nearly-exact linear systems and observe the emergence of semantic concepts. Despite their expressive power and global nonlinearity, modern LLMs can be interpreted through nearly-exact locally linear decompositions that provide insights into their internal representations and reveal interpretable semantic structures in the next-token prediction process.

Vision-language models are increasingly deployed in high-stakes settings, yet their susceptibility to sycophantic manipulation remains poorly understood, particularly in relation to how these models represent visual information internally. Whether models whose visual representations more closely mirror human neural processing are also more resistant to adversarial pressure is an open question with implications for both neuroscience and AI safety. We investigate this question by evaluating 12 open-weight vision-language models spanning 6 architecture families and a 40times parameter range (256M--10B) along two axes: brain alignment, measured by predicting fMRI responses from the Natural Scenes Dataset across 8 human subjects and 6 visual cortex regions of interest, and sycophancy, measured through 76,800 two-turn gaslighting prompts spanning 5 categories and 10 difficulty levels. Region-of-interest analysis reveals that alignment specifically in early visual cortex (V1--V3) is a reliable negative predictor of sycophancy (r = -0.441, BCa 95\% CI [-0.740, -0.031]), with all 12 leave-one-out correlations negative and the strongest effect for existence denial attacks (r = -0.597, p = 0.040). This anatomically specific relationship is absent in higher-order category-selective regions, suggesting that faithful low-level visual encoding provides a measurable anchor against adversarial linguistic override in vision-language models. We release our code on https://github.com/aryashah2k/Gaslight-Gatekeep-Sycophantic-Manipulation{GitHub} and dataset on https://huggingface.co/datasets/aryashah00/Gaslight-Gatekeep-V1-V3{Hugging Face}

In August 2025, OpenAI released GPT-OSS models, its first open weight large language models since GPT-2 in 2019, comprising two mixture of experts architectures with 120B and 20B parameters. We evaluated both variants against six contemporary open source large language models ranging from 14.7B to 235B parameters, representing both dense and sparse designs, across ten benchmarks covering general knowledge, mathematical reasoning, code generation, multilingual understanding, and conversational ability. All models were tested in unquantised form under standardised inference settings, with statistical validation using McNemars test and effect size analysis. Results show that gpt-oss-20B consistently outperforms gpt-oss-120B on several benchmarks, such as HumanEval and MMLU, despite requiring substantially less memory and energy per response. Both models demonstrate mid-tier overall performance within the current open source landscape, with relative strength in code generation and notable weaknesses in multilingual tasks. These findings provide empirical evidence that scaling in sparse architectures may not yield proportional performance gains, underscoring the need for further investigation into optimisation strategies and informing more efficient model selection for future open source deployments.

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often accompanied by catastrophic forgetting of the base model's capabilities, severely limiting the usefulness of the resulting model. We address this issue by proposing Branch-and-Merge (BaM), a new adaptation method based on iteratively merging multiple models, fine-tuned on a subset of the available training data. BaM is based on the insight that this yields lower magnitude but higher quality weight changes, reducing forgetting of the source domain while maintaining learning on the target domain. We demonstrate in an extensive empirical study on Bulgarian and German that BaM can significantly reduce forgetting while matching or even improving target domain performance compared to both standard continued pretraining and instruction finetuning across different model architectures.

As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no standard approach to evaluate tamper resistance. Varied data sets, metrics, and tampering configurations make it difficult to compare safety, utility, and robustness across different models and defenses. To this end, we introduce TamperBench, the first unified framework to systematically evaluate the tamper resistance of LLMs. TamperBench (i) curates a repository of state-of-the-art weight-space fine-tuning attacks and latent-space representation attacks; (ii) enables realistic adversarial evaluation through systematic hyperparameter sweeps per attack-model pair; and (iii) provides both safety and utility evaluations. TamperBench requires minimal additional code to specify any fine-tuning configuration, alignment-stage defense method, and metric suite while ensuring end-to-end reproducibility. We use TamperBench to evaluate 21 open-weight LLMs, including defense-augmented variants, across nine tampering threats using standardized safety and capability metrics with hyperparameter sweeps per model-attack pair. This yields novel insights, including effects of post-training on tamper resistance, that jailbreak-tuning is typically the most severe attack, and that Triplet emerges as a leading alignment-stage defense. Code is available at: https://github.com/criticalml-uw/TamperBench

We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of 756 images of pairwise non-intersecting Jordan curves across easy, polygonal, topographic-inspired, maze-like, and dense counting configurations. Each image is annotated with a rooted tree encoding the containment relations between planar regions. We formulate the task as structured prediction: given an image, a model must recover the full rooted containment tree induced by the curves. Despite the visual simplicity of the task, the strongest evaluated model, Gemini 3.1 Pro, achieves only 71.1\% tree-generation accuracy on CurveBench-Easy and 19.1\% on CurveBench-Hard. We further demonstrate benchmark utility through RLVR-style fine-tuning of open-weight vision-language models. Our trained Qwen3-VL-8B model improves over Qwen-3-VL-8B-Thinking from 2.8\% to 33.3\% tree-generation accuracy on CurveBench-Easy, exceeding GPT-5.4 and Claude Opus 4.5 under our evaluation protocol. The remaining gap, especially on CurveBench-Hard, shows that exact topology-aware visual reasoning remains far from solved.

The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Language Models (SLMs). However, they suffer from a fundamental capability gap: unlike frontier large models, they lack the inference-time strong generalization to work with complicated, unfamiliar codebases. We identify that the prevailing Task-Centric Learning (TCL) paradigm, which scales exposure across disparate repositories, fails to address this limitation. In response, we propose Repository-Centric Learning (RCL), a paradigm shift that prioritizes vertical repository depth over horizontal task breadth, suggesting SLMs must internalize the "physics" of a target software environment through parametric knowledge acquisition, rather than attempting to recover it via costly inference-time search. Following this new paradigm, we design a four-unit Repository-Centric Experience, transforming static codebases into interactive learning signals, to train SWE-Spot-4B, a family of highly compact models built as repo-specialized experts that breaks established scaling trends, outperforming open-weight models up to larger (e.g., CWM by Meta, Qwen3-Coder-30B) and surpassing/matching efficiency-focused commercial models (e.g., GPT-4.1-mini, GPT-5-nano) across multiple SWE tasks. Further analysis reveals that RCL yields higher training sample efficiency and lower inference costs, emphasizing that for building efficient intelligence, repository mastery is a distinct and necessary dimension that complements general coding capability.

Accurate text recognition for historical documents can greatly advance the study and preservation of cultural heritage. Existing vision-language models (VLMs), however, are designed for modern, standardized texts and are not equipped to read the diverse languages and scripts, irregular layouts, and frequent degradation found in historical materials. This paper presents CHURRO, a 3B-parameter open-weight VLM specialized for historical text recognition. The model is trained on CHURRO-DS, the largest historical text recognition dataset to date. CHURRO-DS unifies 155 historical corpora comprising 99,491 pages, spanning 22 centuries of textual heritage across 46 language clusters, including historical variants and dead languages. We evaluate several open-weight and closed VLMs and optical character recognition (OCR) systems on CHURRO-DS and find that CHURRO outperforms all other VLMs. On the CHURRO-DS test set, CHURRO achieves 82.3% (printed) and 70.1% (handwritten) normalized Levenshtein similarity, surpassing the second-best model, Gemini 2.5 Pro, by 1.4% and 6.5%, respectively, while being 15.5 times more cost-effective. By releasing the model and dataset, we aim to enable community-driven research to improve the readability of historical texts and accelerate scholarship.

We present TMMLU+, a new benchmark designed for Traditional Chinese language understanding. TMMLU+ is a multi-choice question-answering dataset with 66 subjects from elementary to professional level. It is six times larger and boasts a more balanced subject distribution than its predecessor, Taiwan Massive Multitask Language Understanding (TMMLU). We also benchmark closed-source models and 26 open-weight Chinese large language models (LLMs) of parameters ranging from 1.8B to 72B on the proposed TMMLU+. Our findings reveal that (1.) Traditional Chinese models still trail behind their Simplified Chinese counterparts, highlighting a need for more focused advancements in LLMs catering to Traditional Chinese. (2.) Current LLMs still fall short of human performance in average scores, indicating a potential need for future research to delve deeper into social science and humanities subjects. (3.) Among all the tokenization compression metrics examined, we identify that only the fertility score uniquely demonstrates strong correlations with our benchmark results. We foresee that TMMLU+ will pinpoint areas for future model improvement, thereby narrowing the gap between machine and human linguistic capabilities and supporting researchers in developing Traditional Chinese LLMs. Our dataset, along with the benchmark source code, is accessible at huggingface.co/datasets/ikala/tmmluplus.

While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, they struggle to comprehend hand-drawn sketches, a modality that offers an intuitive means of expressing concepts that are difficult to describe textually. We identify the primary bottleneck as the absence of a large-scale dataset that jointly models sketches, photorealistic images, and corresponding natural language instructions. To address this, we present two key contributions: (1) a new, large-scale dataset of image-sketch-instruction triplets designed to facilitate both pretraining and instruction tuning, and (2) O3SLM, an LVLM trained on this dataset. Comprehensive evaluations on multiple sketch-based tasks: (a) object localization, (b) counting, (c) image retrieval i.e., (SBIR and fine-grained SBIR), and (d) visual question answering (VQA); while incorporating the three existing sketch datasets, namely QuickDraw!, Sketchy, and Tu Berlin, along with our generated SketchVCL dataset, show that O3SLM achieves state-of-the-art performance, substantially outperforming existing LVLMs in sketch comprehension and reasoning.

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially open, limiting transparency and reproducibility. In this work, we introduce Instella, a family of fully open three billion parameter language models trained entirely on openly available data and codebase. Powered by AMD Instinct MI300X GPUs, Instella is developed through large-scale pre-training, general-purpose instruction tuning, and alignment with human preferences. Despite using substantially fewer pre-training tokens than many contemporaries, Instella achieves state-of-the-art results among fully open models and is competitive with leading open-weight models of comparable size. We further release two specialized variants: Instella-Long, capable of handling context lengths up to 128K tokens, and Instella-Math, a reasoning-focused model enhanced through supervised fine-tuning and reinforcement learning on mathematical tasks. Together, these contributions establish Instella as a transparent, performant, and versatile alternative for the community, advancing the goal of open and reproducible language modeling research.

The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern open LLMs, and how does this magnitude vary across families, generations, and training stages? Under a unified pipeline (5,000-sample multi-domain corpus, family-specific tokenization, identical hooks across embeddings, hidden states, attention, MLP/MoE, SwiGLU gates, and final norm), we measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE, vision-language, intermediate-training, and instruction-tuned variants. We find that (i) global maxima span over nearly four orders of magnitude at comparable parameter counts, with Qwen3.5 and MoE checkpoints in the 10^2 to 10^3 range and Gemma3-27B-it reaching ~7 x 10^5; (ii) cross-family and cross-generation comparisons break simple monotonic scaling; and (iii) MoE checkpoints exhibit 14.0-23.4x lower peaks than matched-scale dense counterparts, while the residual stream carries the global maximum in 22/24 checkpoints. A lightweight INT-8 sanity check shows that measured maxima co-vary with low-bit reconstruction error via activation-scale selection. We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size - and should be measured and reported alongside any open-weight release before low-bit deployment. The code is publicly available at https://github.com/clx1415926/Max_act_llm.

We present Audio Flamingo Next (AF-Next), the next-generation and most capable large audio-language model in the Audio Flamingo series, designed to advance understanding and reasoning over speech, environmental sounds and music. Compared to Audio Flamingo 3, AF-Next introduces: (i) a stronger foundational audio-language model that significantly improves accuracy across diverse audio understanding tasks; (ii) scalable strategies for constructing large-scale audio understanding and reasoning data beyond existing academic benchmarks; (iii) support for long and complex audio inputs up to 30 minutes; and (iv) Temporal Audio Chain-of-Thought, a new reasoning paradigm that explicitly grounds intermediate reasoning steps to timestamps in long audio, enabling fine-grained temporal alignment and improved interpretability. To enable these capabilities, we first conduct a systematic analysis of Audio Flamingo 3 to identify key gaps in audio understanding and reasoning. We then curate and scale new large-scale datasets totaling over 1 million hours to address these limitations and expand the existing AudioSkills-XL, LongAudio-XL, AF-Think and AF-Chat datasets. AF-Next is trained using a curriculum-based strategy spanning pre-training, mid-training and post-training stages. Extensive experiments across 20 audio understanding and reasoning benchmarks, including challenging long-audio tasks, show that AF-Next outperforms similarly sized open models by large margins and remains highly competitive with and sometimes surpasses, much larger open-weight and closed models. Beyond benchmark performance, AF-Next exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability. In addition to all data, code and methods, we open-source 3 variants of AF-Next, including AF-Next-Instruct, AF-Next-Think and AF-Next-Captioner.

Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives with explicit ethical lessons. We close this gap with TF1-EN-3M, the first open dataset of three million English-language fables generated exclusively by instruction-tuned models no larger than 8B parameters. Each story follows a six-slot scaffold (character -> trait -> setting -> conflict -> resolution -> moral), produced through a combinatorial prompt engine that guarantees genre fidelity while covering a broad thematic space. A hybrid evaluation pipeline blends (i) a GPT-based critic that scores grammar, creativity, moral clarity, and template adherence with (ii) reference-free diversity and readability metrics. Among ten open-weight candidates, an 8B-parameter Llama-3 variant delivers the best quality-speed trade-off, producing high-scoring fables on a single consumer GPU (<24 GB VRAM) at approximately 13.5 cents per 1,000 fables. We release the dataset, generation code, evaluation scripts, and full metadata under a permissive license, enabling exact reproducibility and cost benchmarking. TF1-EN-3M opens avenues for research in instruction following, narrative intelligence, value alignment, and child-friendly educational AI, demonstrating that large-scale moral storytelling no longer requires proprietary giant models.

We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) long audio understanding and reasoning (including speech) up to 10 minutes; and (v) voice-to-voice interaction. To enable these capabilities, we propose several large-scale training datasets curated using novel strategies, including AudioSkills-XL, LongAudio-XL, AF-Think, and AF-Chat, and train AF3 with a novel five-stage curriculum-based training strategy. Trained on only open-source audio data, AF3 achieves new SOTA results on over 20+ (long) audio understanding and reasoning benchmarks, surpassing both open-weight and closed-source models trained on much larger datasets.

Large Language Model (LLM) safety is one of the most pressing challenges for enabling wide-scale deployment. While most studies and global discussions focus on generic harms, such as models assisting users in harming themselves or others, enterprises face a more fundamental concern: whether LLM-based agents are safe for their intended use case. To address this, we introduce operational safety, defined as an LLM's ability to appropriately accept or refuse user queries when tasked with a specific purpose. We further propose OffTopicEval, an evaluation suite and benchmark for measuring operational safety both in general and within specific agentic use cases. Our evaluations on six model families comprising 20 open-weight LLMs reveal that while performance varies across models, all of them remain highly operationally unsafe. Even the strongest models -- Qwen-3 (235B) with 77.77\% and Mistral (24B) with 79.96\% -- fall far short of reliable operational safety, while GPT models plateau in the 62--73\% range, Phi achieves only mid-level scores (48--70\%), and Gemma and Llama-3 collapse to 39.53\% and 23.84\%, respectively. While operational safety is a core model alignment issue, to suppress these failures, we propose prompt-based steering methods: query grounding (Q-ground) and system-prompt grounding (P-ground), which substantially improve OOD refusal. Q-ground provides consistent gains of up to 23\%, while P-ground delivers even larger boosts, raising Llama-3.3 (70B) by 41\% and Qwen-3 (30B) by 27\%. These results highlight both the urgent need for operational safety interventions and the promise of prompt-based steering as a first step toward more reliable LLM-based agents.

The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at developing a suite of open-weight multilingual LLMs capable of understanding and generating text in all official European Union languages, as well as several additional relevant languages. We outline the progress made to date, detailing our data collection and filtering process, the development of scaling laws, the creation of our multilingual tokenizer, and the data mix and modeling configurations. Additionally, we release our initial models: EuroLLM-1.7B and EuroLLM-1.7B-Instruct and report their performance on multilingual general benchmarks and machine translation.

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work, we introduce MeasureBench, a benchmark on visual measurement reading covering both real-world and synthesized images of various types of measurements, along with an extensible pipeline for data synthesis. Our pipeline procedurally generates a specified type of gauge with controllable visual appearance, enabling scalable variation in key details such as pointers, scales, fonts, lighting, and clutter. Evaluation on popular proprietary and open-weight VLMs shows that even the strongest frontier VLMs struggle measurement reading in general. A consistent failure mode is indicator localization: models can read digits or labels but misidentify the key positions of pointers or alignments, leading to big numeric errors despite plausible textual reasoning. We have also conducted preliminary experiments with reinforcement learning over synthetic data, and find encouraging results on in-domain synthetic subset but less promising for real-world images. Our analysis highlights a fundamental limitation of current VLMs in fine-grained spatial grounding. We hope this resource can help future advances on visually grounded numeracy and precise spatial perception of VLMs, bridging the gap between recognizing numbers and measuring the world.

We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maze, operant chamber, shuttle box, conditioned place preference, and delayed non-match to sample), spanning six cognitive dimensions. Each task is grounded in peer-reviewed rodent protocols with approximate animal baselines. The agent receives a unified system prompt with no task-specific instructions and must discover goals purely from ASCII text observations and reward signals, much like a rodent placed into an unfamiliar apparatus. We evaluate six open-weight LLMs (3B to 72B parameters) on text-based ASCII renderings and compare against both a random baseline and a graph-based reinforcement learning agent. Our best model (Qwen2.5-VL-7B) reaches 52.6% average success on ASCII input, compared to 32.1% for random agents and 78.9% for approximate rodent baselines. We find that (1) scaling beyond 7B yields diminishing returns, (2) longer context history degrades performance, (3) chain-of-thought prompting hurts rather than helps, and (4) a vision-language architecture provides an advantage at 7B but hurts at 32B. Because the same model's performance ranges from 20% to 57% depending on interface parameters alone, these results characterize the agent-plus-interface system, not the model in isolation. Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly in tasks requiring advanced reasoning. Large reasoning models, which leverage long chain-of-thoughts, bring unprecedented breakthroughs in problem-solving capabilities but at a substantial deployment cost associated to longer generations. Reducing inference costs is crucial for the economic feasibility, user experience, and environmental sustainability of these models. In this work, we propose to train large reasoning models to reason efficiently. More precisely, we use reinforcement learning (RL) to train reasoning models to dynamically allocate inference-time compute based on task complexity. Our method incentivizes models to minimize unnecessary computational overhead while maintaining accuracy, thereby achieving substantial efficiency gains. It enables the derivation of a family of reasoning models with varying efficiency levels, controlled via a single hyperparameter. Experiments on two open-weight large reasoning models demonstrate significant reductions in inference cost while preserving most of the accuracy.

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific descriptions, or vulnerability-reproduction tasks. We present SEC-bench Pro, a benchmark for measuring agent bug hunting on critical, high-complexity software systems. This work discloses reports with concrete PoC inputs and links fixes into reproducible tasks through a three-phase pipeline for vulnerability collection, environment reconstruction, and oracle-based validation. We instantiate SEC-bench Pro with 183 validated vulnerabilities across V8 and SpiderMonkey, including a V8 subset with more than $1.5 million in cumulative Google Vulnerability Reward Program awards. These instances span memory-safety, sandbox, JIT, and race-condition bugs under browser-grade and runtime-grade execution conditions. Our evaluation shows that coding agents with frontier models remain below 40% success on both evaluated engines. The open-weight Kimi-K2.6 baseline reaches 11.7% on V8, while the strongest frontier configuration reaches 32.0% on V8 and 38.8% on SpiderMonkey. ClaudeCode and Codex solve complementary instance sets, and their two-agent union reaches 37.9% on V8 and 48.8% on SpiderMonkey. SEC-bench Pro provides robust environments for assessing LLM-based security agents and exposes limitations in long-horizon bug hunting tasks.

Large Language Models (LLMs) offer state-of-the-art performance in natural language understanding and generation tasks. However, the deployment of leading commercial models for specialized tasks, such as e-commerce, is often hindered by high computational costs, latency, and operational expenses. This paper investigates the viability of smaller, open-weight models as a resource-efficient alternative. We present a methodology for optimizing a one-billion-parameter Llama 3.2 model for multilingual e-commerce intent recognition. The model was fine-tuned using Quantized Low-Rank Adaptation (QLoRA) on a synthetically generated dataset designed to mimic real-world user queries. Subsequently, we applied post-training quantization techniques, creating GPU-optimized (GPTQ) and CPU-optimized (GGUF) versions. Our results demonstrate that the specialized 1B model achieves 99% accuracy, matching the performance of the significantly larger GPT-4.1 model. A detailed performance analysis revealed critical, hardware-dependent trade-offs: while 4-bit GPTQ reduced VRAM usage by 41%, it paradoxically slowed inference by 82% on an older GPU architecture (NVIDIA T4) due to dequantization overhead. Conversely, GGUF formats on a CPU achieved a speedup of up to 18x in inference throughput and a reduction of over 90% in RAM consumption compared to the FP16 baseline. We conclude that small, properly optimized open-weight models are not just a viable but a more suitable alternative for domain-specific applications, offering state-of-the-art accuracy at a fraction of the computational cost.

Despite increasing discussions on open-source Artificial Intelligence (AI), existing research lacks a discussion on the transparency and accessibility of state-of-the-art (SoTA) Large Language Models (LLMs). The Open Source Initiative (OSI) has recently released its first formal definition of open-source software. This definition, when combined with standard dictionary definitions and the sparse published literature, provide an initial framework to support broader accessibility to AI models such as LLMs, but more work is essential to capture the unique dynamics of openness in AI. In addition, concerns about open-washing, where models claim openness but lack full transparency, has been raised, which limits the reproducibility, bias mitigation, and domain adaptation of these models. In this context, our study critically analyzes SoTA LLMs from the last five years, including ChatGPT, DeepSeek, LLaMA, and others, to assess their adherence to transparency standards and the implications of partial openness. Specifically, we examine transparency and accessibility from two perspectives: open-source vs. open-weight models. Our findings reveal that while some models are labeled as open-source, this does not necessarily mean they are fully open-sourced. Even in the best cases, open-source models often do not report model training data, and code as well as key metrics, such as weight accessibility, and carbon emissions. To the best of our knowledge, this is the first study that systematically examines the transparency and accessibility of over 100 different SoTA LLMs through the dual lens of open-source and open-weight models. The findings open avenues for further research and call for responsible and sustainable AI practices to ensure greater transparency, accountability, and ethical deployment of these models.(DeepSeek transparency, ChatGPT accessibility, open source, DeepSeek open source)

Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE, which evaluates the ALMs on avoiding stereotypes, and CoRe-Bench, which measures reasoning over conversational audio through inferential multi-turn question answering -- to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs: audio perception, knowledge, reasoning, emotion detection, bias, fairness, multilinguality, robustness, toxicity, and safety. We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models. We test 14 open-weight and closed-API ALMs from 3 developers and 3 additional simple baseline systems each consisting of an automatic speech recognizer and a language model. Our results show that while Gemini 2.5 Pro ranks top in 5 out of 10 aspects, it exhibits group unfairness (p=0.01) on ASR tasks whereas most of the other models do not. We also find that the baseline systems perform reasonably well on AHELM, with one ranking 5th overall despite having only speech-to-text capabilities. For transparency, all raw prompts, model generations, and outputs are available on our website at https://crfm.stanford.edu/helm/audio/v1.0.0. AHELM is intended to be a living benchmark and new datasets and models will be added over time.

We apply preference learning to the task of language model-guided design of novel structural alloys. In contrast to prior work that focuses on generating stable inorganic crystals, our approach targets the synthesizeability of a specific structural class: BCC/B2 superalloys, an underexplored family of materials with potential applications in extreme environments. Using three open-weight models (LLaMA-3.1, Gemma-2, and OLMo-2), we demonstrate that language models can be optimized for multiple design objectives using a single, unified reward signal through Direct Preference Optimization (DPO). Unlike prior approaches that rely on heuristic or human-in-the-loop feedback (costly), our reward signal is derived from thermodynamic phase calculations, offering a scientifically grounded criterion for model tuning. To our knowledge, this is the first demonstration of preference-tuning a language model using physics-grounded feedback for structural alloy design. The resulting framework is general and extensible, providing a path forward for intelligent design-space exploration across a range of physical science domains.

Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, little is known about the frequently used chat template's effect on the calibration of conversational LLMs. In this work, we investigate the mechanisms driving this miscalibration by decoupling the effects of the post-training algorithm and the chat format. We find that, while instruction tuning fundamentally harms calibration, the chat template aggravates the issue through an "ownership bias" -- models are significantly more confident in their own answers than in identical answers provided by a user. Extensive experiments across six recent open-weight LLMs, three benchmarks, and three confidence elicitation methods show that models assign up to 26% higher confidence to their own responses. Leveraging this insight, we propose a simple inference-time strategy: framing the model's answer as user input during confidence elicitation. This approach significantly reduces overconfidence and improves calibration by up to 26% without the need for retraining, narrowing the gap between base and instruction-tuned models.

Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models (3-9B parameters, four families) produce verbalised confidence that meets minimal validity criteria for item-level Type-2 discrimination under minimal numeric elicitation with greedy decoding. In a pre-registered study (OSF: osf.io/azbvx), 524 TriviaQA items were administered under numeric (0-100) and categorical (10-class) elicitation to eight models at Q5_K_M quantisation on consumer hardware, yielding 8,384 deterministic trials. A psychometric validity screen was applied to each model-format cell. All seven instruct models were classified Invalid on numeric confidence (H2 confirmed, 7/7 vs. predicted >=4/7), with a mean ceiling rate of 91.7% (H1 confirmed). Categorical elicitation did not rescue validity. Instead, it disrupted task performance in six of seven models, producing accuracy below 5% (H4 not confirmed). Token-level logprobability did not usefully predict verbalised confidence under the observed variance regime (H5 confirmed, mean cross-validated R^2 < 0.01). Within the reasoning-distilled model, reasoning-trace length showed a strong negative partial correlation with confidence (rho = -0.36, p < .001), consistent with the Reasoning Contamination Effect. These results do not imply that internal uncertainty representations are absent. They show that minimal verbal elicitation fails to preserve internal signals at the output interface in this model-size regime. Psychometric screening should precede any downstream use of such signals.

Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese is included in several multilingual benchmarks, these resources do not adequately capture the language-specific complexities. Meanwhile, existing Japanese visual text datasets have primarily focused on scanned documents, leaving in-the-wild scene text underexplored. To fill this gap, we introduce JaWildText, a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding. JaWildText contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types. It comprises three complementary tasks that vary in visual organization, output format, and writing style: (i) Dense Scene Text Visual Question Answering (STVQA), which requires reasoning over multiple pieces of visual text evidence; (ii) Receipt Key Information Extraction (KIE), which tests layout-aware structured extraction from mobile-captured receipts; and (iii) Handwriting OCR, which evaluates page-level transcription across various media and writing directions. We evaluate 14 open-weight VLMs and find that the best model achieves an average score of 0.64 across the three tasks. Error analyses show recognition remains the dominant bottleneck, especially for kanji. JaWildText enables fine-grained, script-aware diagnosis of Japanese scene text capabilities, and will be released with evaluation code.

Recent advances in multimodal large language models enable new possibilities for image-based decision support. However, their reliability and operational trade-offs in neuroimaging remain insufficiently understood. We present a comprehensive benchmarking study of vision-enabled large language models for 2D neuroimaging using curated MRI and CT datasets covering multiple sclerosis, stroke, brain tumors, other abnormalities, and normal controls. Models are required to generate multiple outputs simultaneously, including diagnosis, diagnosis subtype, imaging modality, specialized sequence, and anatomical plane. Performance is evaluated across four directions: discriminative classification with abstention, calibration, structured-output validity, and computational efficiency. A multi-phase framework ensures fair comparison while controlling for selection bias. Across twenty frontier multimodal models, the results show that technical imaging attributes such as modality and plane are nearly solved, whereas diagnostic reasoning, especially subtype prediction, remains challenging. Tumor classification emerges as the most reliable task, stroke is moderately solvable, while multiple sclerosis and rare abnormalities remain difficult. Few-shot prompting improves performance for several models but increases token usage, latency, and cost. Gemini-2.5-Pro and GPT-5-Chat achieve the strongest overall diagnostic performance, while Gemini-2.5-Flash offers the best efficiency-performance trade-off. Among open-weight architectures, MedGemma-1.5-4B demonstrates the most promising results, as under few-shot prompting, it approaches the zero-shot performance of several proprietary models, while maintaining perfect structured output. These findings provide practical insights into performance, reliability, and efficiency trade-offs, supporting standardized evaluation of multimodal LLMs in neuroimaging.

Information retrieval (IR) systems have played a vital role in modern digital life and have cemented their continued usefulness in this new era of generative AI via retrieval-augmented generation. With strong language processing capabilities and remarkable versatility, large language models (LLMs) have become popular choices for zero-shot re-ranking in IR systems. So far, LLM-based re-ranking methods rely on strong generative capabilities, which restricts their use to either specialized or powerful proprietary models. Given these restrictions, we ask: is autoregressive generation necessary and optimal for LLMs to perform re-ranking? We hypothesize that there are abundant signals relevant to re-ranking within LLMs that might not be used to their full potential via generation. To more directly leverage such signals, we propose in-context re-ranking (ICR), a novel method that leverages the change in attention pattern caused by the search query for accurate and efficient re-ranking. To mitigate the intrinsic biases in LLMs, we propose a calibration method using a content-free query. Due to the absence of generation, ICR only requires two (O(1)) forward passes to re-rank N documents, making it substantially more efficient than generative re-ranking methods that require at least O(N) forward passes. Our novel design also enables ICR to be applied to any LLM without specialized training while guaranteeing a well-formed ranking. Extensive experiments with two popular open-weight LLMs on standard single-hop and multi-hop information retrieval benchmarks show that ICR outperforms RankGPT while cutting the latency by more than 60% in practice. Through detailed analyses, we show that ICR's performance is specially strong on tasks that require more complex re-ranking signals. Our findings call for further exploration on novel ways of utilizing open-weight LLMs beyond text generation.

Retrieval-Augmented Generation (RAG) is a framework in which a Generator, such as a Large Language Model (LLM), produces answers by retrieving documents from an external collection using a Retriever. In practice, Generators must integrate evidence from long contexts, perform multi-step reasoning, interpret tables, and abstain when evidence is missing. However, existing benchmarks for Generators provide limited coverage, with none enabling simultaneous evaluation of multiple capabilities under unified conditions. To bridge the gap between existing evaluations and practical use, we introduce LIT-RAGBench (the Logic, Integration, Table, Reasoning, and Abstention RAG Generator Benchmark), which defines five categories: Integration, Reasoning, Logic, Table, and Abstention, each further divided into practical evaluation aspects. LIT-RAGBench systematically covers patterns combining multiple aspects across categories. By using fictional entities and scenarios, LIT-RAGBench evaluates answers grounded in the provided external documents. The dataset consists of 114 human-constructed Japanese questions and an English version generated by machine translation with human curation. We use LLM-as-a-Judge for scoring and report category-wise and overall accuracy. Across API-based and open-weight models, no model exceeds 90% overall accuracy. By making strengths and weaknesses measurable within each category, LIT-RAGBench serves as a valuable metric for model selection in practical RAG deployments and for building RAG-specialized models. We release LIT-RAGBench, including the dataset and evaluation code, at https://github.com/Koki-Itai/LIT-RAGBench.

LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In this work, we focus on a prerequisite for foundational innovation: can LLMs reinvent foundational algorithms in computer science? Our Unlearn-and-Reinvent pipeline applies LLM unlearning to remove a specific foundational algorithm, such as Dijkstra's or Euclid's algorithm, from an LLM's pretrained knowledge, and then tests whether the model can reinvent it in a controlled environment. To enable effective unlearning, we adopt a GRPO-based, on-policy unlearning method. Across 10 target algorithms, 3 strong open-weight models, and 3 hint levels, our experiments demonstrate that (1) the strongest model Qwen3-4B-Thinking-2507 successfully reinvents 50% of the algorithms with no hint, 70% at hint level 1, and 90% at hint level 2; (2) a few high-level hints can enhance the reinvention success rate, but even step-by-step hints fail for those complicated algorithms; and (3) test-time reinforcement learning enables successful reinvention for the Strassen algorithm at hint level 2. Through analyses of output trajectories and ablation studies, we find that generative verifier in the reinvention phase plays a critical role in sustaining models' reasoning strength, helping to avoid the ``thought collapse'' phenomenon. These findings offer insights into both the potential and current limits of LLMs' innovative thinking.

Competitive programming problems increasingly serve as valuable benchmarks to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as lack of exceptionally challenging problems, insufficient test case coverage, reliance on online platform APIs that limit accessibility. To address these issues, we introduce LiveOIBench, a comprehensive benchmark featuring 403 expert-curated Olympiad-level competitive programming problems, each with an average of 60 expert-designed test cases. The problems are sourced directly from 72 official Informatics Olympiads in different regions conducted between 2023 and 2025. LiveOIBench distinguishes itself through four key features: (1) meticulously curated high-quality tasks with detailed subtask rubrics and extensive private test cases; (2) direct integration of elite contestant performance data to enable informative comparison against top-performing humans; (3) planned continuous, contamination-free updates from newly released Olympiad problems; and (4) a self-contained evaluation system facilitating offline and easy-to-reproduce assessments. Benchmarking 32 popular general-purpose and reasoning LLMs, we find that GPT-5 achieves a notable 81.76th percentile, a strong result that nonetheless falls short of top human contestant performance, who usually place above 90th. In contrast, among open-weight reasoning models, GPT-OSS-120B achieves only a 60th percentile, underscoring significant capability disparities from frontier closed models. Detailed analyses indicate that robust reasoning models prioritize precise problem analysis over excessive exploration, suggesting future models should emphasize structured analysis and minimize unnecessary exploration. All data, code, and leaderboard results will be made publicly available on our website.

Large Language Models are versatile general-task solvers, and their capabilities can truly assist people with scholarly peer review as pre-review agents, if not as fully autonomous peer-review agents. While incredibly beneficial, automating academic peer-review, as a concept, raises concerns surrounding safety, research integrity, and the validity of the academic peer-review process. The majority of the studies performing a systematic evaluation of frontier LLMs generating reviews across science disciplines miss the mark on addressing the alignment/misalignment of reviews along with the utility of LLM generated reviews when compared against publication outcomes such as Citations, Hit-papers, Novelty, and Disruption. This paper presents an experimental study in which we gathered ground-truth reviewer ratings from OpenReview and used various frontier open-weight LLMs to generate reviews of papers to gauge the safety and reliability of incorporating LLMs into the scientific review pipeline. Our findings demonstrate the utility of frontier open-weight LLMs as pre-review screening agents despite highlighting fundamental misalignment risks when deployed as autonomous reviewers. Our results show that all models exhibit weak correlation with human peer reviewers (0.15), with systematic overestimation bias of 3-5 points and uniformly high confidence scores (8.0-9.0/10) despite prediction errors. However, we also observed that LLM reviews correlate more strongly with post-publication metrics than with human scores, suggesting potential utility as pre-review screening tools. Our findings highlight the potential and address the pitfalls of automating peer reviews with language models. We open-sourced our dataset D_{LMRSD} to help the research community expand the safety framework of automating scientific reviews.

We present DialectalArabicMMLU, a new benchmark for evaluating the performance of large language models (LLMs) across Arabic dialects. While recently developed Arabic and multilingual benchmarks have advanced LLM evaluation for Modern Standard Arabic (MSA), dialectal varieties remain underrepresented despite their prevalence in everyday communication. DialectalArabicMMLU extends the MMLU-Redux framework through manual translation and adaptation of 3K multiple-choice question-answer pairs into five major dialects (Syrian, Egyptian, Emirati, Saudi, and Moroccan), yielding a total of 15K QA pairs across 32 academic and professional domains (22K QA pairs when also including English and MSA). The benchmark enables systematic assessment of LLM reasoning and comprehension beyond MSA, supporting both task-based and linguistic analysis. We evaluate 19 open-weight Arabic and multilingual LLMs (1B-13B parameters) and report substantial performance variation across dialects, revealing persistent gaps in dialectal generalization. DialectalArabicMMLU provides the first unified, human-curated resource for measuring dialectal understanding in Arabic, thus promoting more inclusive evaluation and future model development.

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data and provide agents with the visual reasoning necessary for new applications in areas such as computer automation. However, agent tasks emphasize skills where accessible open-weight VLMs lag behind their LLM equivalents. For example, VLMs are less capable of following an environment's strict output syntax requirements and are more focused on open-ended question answering. Overcoming these limitations requires supervised fine-tuning (SFT) on task-specific expert demonstrations. Our work approaches these challenges from an offline-to-online reinforcement learning (RL) perspective. RL lets us fine-tune VLMs to agent tasks while learning from the unsuccessful decisions of our own model or more capable (larger) models. We explore an off-policy RL solution that retains the stability and simplicity of the widely used SFT workflow while allowing our agent to self-improve and learn from low-quality datasets. We demonstrate this technique with two open-weight VLMs across three multi-modal agent domains.

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after thousands of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that tamper-resistance is a tractable problem, opening up a promising new avenue to improve the safety and security of open-weight LLMs.

This technical report introduces EXAONE 4.0, which integrates a Non-reasoning mode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reasoning abilities of EXAONE Deep. To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean. The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications. The EXAONE 4.0 demonstrates superior performance compared to open-weight models in its class and remains competitive even against frontier-class models. The models are publicly available for research purposes and can be easily downloaded via https://huggingface.co/LGAI-EXAONE.

Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this work, we systematically study the interplay between perception and reasoning in VLM post-training by decomposing their capabilities into three separate training stages: visual perception, visual reasoning, and textual reasoning, incorporating specialized training data. We demonstrate that visual perception (a) requires targeted optimization with specialized data; (b) serves as a fundamental scaffold that should be solidified through staged training before refining visual reasoning; and (c) is more effectively learned via RL than caption-based SFT. Our experiments across multiple VLMs demonstrate that staged training consistently improves both visual perception and reasoning performance over merged training. Notably, models trained with our approach achieve 1.5% higher reasoning accuracy with 20.8% shorter reasoning traces, suggesting that superior perception reduces the need for excessive reasoning. Furthermore, we show that this capability-based staging represents a new curriculum dimension orthogonal to traditional difficulty-based curricula, and combining both yields further additive gains. Our staged-training models achieve superior performance among open-weight VLMs, establishing advanced results on several visual math and perception (e.g., +5.2% on WeMath and +3.7% on RealWorldQA) tasks compared with the base counterpart.

Collecting ground truth task completion rewards or human demonstrations for multi-step reasoning tasks is often cost-prohibitive and time-consuming, especially in interactive domains like web tasks. To address this bottleneck, we present self-taught lookahead, a self-supervised method that leverages state-transition dynamics to train a value model capable of effectively guiding language model-controlled search. We find that moderately sized (8 billion parameters) open-weight value models improved with self-taught lookahead can match the performance of using a frontier LLM such as gpt-4o as the value model. Furthermore, we find that self-taught lookahead improves performance by 20% while reducing costs 37x compared to previous LLM-based tree search, without relying on ground truth rewards.

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual Encoder, which conditions each visual representation on prior visual features. Under supervised finetuning, VLMs equipped with stateful encoders achieve consistent improvements on controlled tasks involving cross-image spatial aggregation, multi-object visual differencing, and visual trajectory behavior cloning. These improvements are consistent across input resolutions, language model sizes, and VLM backbones. Finally, we validate our model on real-world tasks, including longitudinal radiology, fine-grained image comparison, and remote sensing, where stateful encoders consistently improve generalist VLM baselines and can match or surpass specialized models in selected domains. Project page: https://statefulvisualencoders.github.io/

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a vulnerable attack surface for behavioral control. Building on recent findings on attention sinks and compression valleys, we identify a high-gain region in the residual stream where small, well-aligned perturbations are causally amplified along the autoregressive trajectory--a Causal Amplification Effect (CAE). We exploit this as an attack surface via Sensitivity-Scaled Steering (SSS), a progressive activation-level attack that combines beginning-of-sequence (BOS) anchoring with sensitivity-based reinforcement to focus a limited perturbation budget on the most vulnerable layers and tokens. We show that across multiple open-weight models and four behavioral axes, SSS induces large shifts in evil, hallucination, sycophancy, and sentiment while preserving high coherence and general capabilities, turning activation steering into a concrete security concern for white-box and supply-chain LLM deployments.

We present ONERULER, a multilingual benchmark designed to evaluate long-context language models across 26 languages. ONERULER adapts the English-only RULER benchmark (Hsieh et al., 2024) by including seven synthetic tasks that test both retrieval and aggregation, including new variations of the "needle-in-a-haystack" task that allow for the possibility of a nonexistent needle. We create ONERULER through a two-step process, first writing English instructions for each task and then collaborating with native speakers to translate them into 25 additional languages. Experiments with both open-weight and closed LLMs reveal a widening performance gap between low- and high-resource languages as context length increases from 8K to 128K tokens. Surprisingly, English is not the top-performing language on long-context tasks (ranked 6th out of 26), with Polish emerging as the top language. Our experiments also show that many LLMs (particularly OpenAI's o3-mini-high) incorrectly predict the absence of an answer, even in high-resource languages. Finally, in cross-lingual scenarios where instructions and context appear in different languages, performance can fluctuate by up to 20% depending on the instruction language. We hope the release of ONERULER will facilitate future research into improving multilingual and cross-lingual long-context training pipelines.

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that process negation correctly. Their poor accuracy is due to late-layer attention behavior that promotes simple shortcuts; ablating those attention modules greatly improves accuracy on negation-related questions. Second, we uncover how models process negation. We consider two hypotheses: models could use attention heads that attend to the phrase being negated and suppress related concepts, or they could directly construct a representation of the entire negative phrase (e.g., representing "not gas" as a vector that promotes liquids and solids). We apply a range of observational and causal interpretability techniques on Mistral-7B and Llama-3.1-8B to show that models implement both mechanisms, with the "constructive" mechanism being more prominent. Combined, our work deepens the understanding of LLMs' internals, highlighting construction-dominant computations and the coexistence of competing mechanisms within LLMs.

Vision-Language Models (VLMs) are increasingly deployed in settings where reliable visual grounding carries operational consequences, yet their behavior under progressively coercive prompt phrasing remains undercharacterized. Existing hallucination benchmarks predominantly rely on neutral prompts and binary detection, leaving open how both the incidence and the intensity of fabrication respond to graded linguistic pressure across structurally distinct task types. We present Ghost-100, a procedurally constructed benchmark of 800 synthetically generated images spanning eight categories across three task families: text-illegibility, time-reading, and object-absence, each designed under a negative-ground-truth principle that guarantees the queried target is absent, illegible, or indeterminate by construction. Every image is paired with five prompts drawn from a structured 5-Level Prompt Intensity Framework, holding the image and task identity fixed while varying only directive force, so that tone is isolated as the sole independent variable. We adopt a dual-track evaluation protocol: a rule-based H-Rate measuring the proportion of responses in which a model crosses from grounded refusal into unsupported positive commitment, and a GPT-4o-mini-judged H-Score on a 1-5 scale characterizing the confidence and specificity of fabrication once it occurs. We additionally release a three-stage automated validation workflow, which retrospectively confirms 717 of 800 images as strictly compliant. Evaluating nine open-weight VLMs, we find that H-Rate and H-Score dissociate substantially across model families, reading-style and presence-detection subsets respond to prompt pressure in qualitatively different ways, and several models exhibit non-monotonic sensitivity peaking at intermediate tone levels: patterns that aggregate metrics obscure.

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 MLCommons harmful prompts into verse via a standardized meta-prompt produced ASRs up to 18 times higher than their prose baselines. Outputs are evaluated using an ensemble of 3 open-weight LLM judges, whose binary safety assessments were validated on a stratified human-labeled subset. Poetic framing achieved an average jailbreak success rate of 62% for hand-crafted poems and approximately 43% for meta-prompt conversions (compared to non-poetic baselines), substantially outperforming non-poetic baselines and revealing a systematic vulnerability across model families and safety training approaches. These findings demonstrate that stylistic variation alone can circumvent contemporary safety mechanisms, suggesting fundamental limitations in current alignment methods and evaluation protocols.

In this paper, we introduce MATA, a novel evaluation dataset to assess the ability of Large Language Models (LLMs) in Telugu language, comprising 729 carefully curated multiple-choice and open-ended questions that span diverse linguistic dimensions. We evaluate 11 open-weight and closed-source LLMs on our dataset and present a fine-grained analysis of their performance. Further, we empirically show how LLMs rely on superficial heuristics such as answer position and distractor patterns for multiple-choice questions. Finally, we also compare LLM-as-a-judge evaluation with human evaluation for open-ended questions and draw some conclusions on its reliability in a low-resource language. We argue that such fine-grained evaluation is essential for understanding model limitations and can inform the development of more linguistically capable LLMs, while also serving as a foundation for future research in Telugu NLP.

Large Language Models (LLMs) have achieved remarkable advancements, but their monolithic nature presents challenges in terms of scalability, cost, and customization. This paper introduces the Composition of Experts (CoE), a modular compound AI system leveraging multiple expert LLMs. CoE leverages a router to dynamically select the most appropriate expert for a given input, enabling efficient utilization of resources and improved performance. We formulate the general problem of training a CoE and discuss inherent complexities associated with it. We propose a two-step routing approach to address these complexities that first uses a router to classify the input into distinct categories followed by a category-to-expert mapping to obtain desired experts. CoE offers a flexible and cost-effective solution to build compound AI systems. Our empirical evaluation demonstrates the effectiveness of CoE in achieving superior performance with reduced computational overhead. Given that CoE comprises of many expert LLMs it has unique system requirements for cost-effective serving. We present an efficient implementation of CoE leveraging SambaNova SN40L RDUs unique three-tiered memory architecture. CoEs obtained using open weight LLMs Qwen/Qwen2-7B-Instruct, google/gemma-2-9b-it, google/gemma-2-27b-it, meta-llama/Llama-3.1-70B-Instruct and Qwen/Qwen2-72B-Instruct achieve a score of 59.4 with merely 31 billion average active parameters on Arena-Hard and a score of 9.06 with 54 billion average active parameters on MT-Bench.

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas such as multilingual safety, exaggerated safety, and prompt injections. The framework supports both LLM and judge benchmarking, and incorporates custom mutators to test safety against various text-style mutations such as future tense and paraphrasing. Additionally, WalledEval introduces WalledGuard, a new, small and performant content moderation tool, and SGXSTest, a benchmark for assessing exaggerated safety in cultural contexts. We make WalledEval publicly available at https://github.com/walledai/walledevalA.

Large Language Models are increasingly being deployed to extract structured data from unstructured and semi-structured sources: parsing invoices, medical records, and converting PDF documents to database entries. Yet existing benchmarks for structured output generation either focus on schema compliance alone, or evaluate value correctness within a single source domain. We introduce SOB (The Structured Output Benchmark), a multi-source benchmark spanning three source modalities: native text, images, and audio conversations. All models receive a text-normalized representation of their context regardless of source modality; this deliberate design isolates structured-output capability from raw vision or speech-processing quality, ensuring a fair, source-agnostic comparison. Our benchmark comprises 5,000 text evaluation records derived from multi-hop QA drawn from a 25,091-record full corpus, 209 image records from OCR-processed PDFs across seven document types including multi-column layouts, dense tables, scanned historical documents, small-print text, and mathematical typesetting, and 115 audio records from the AMI corpus. Each record pairs a natural-language question with a JSON schema that the model must follow and a ground-truth answer verified against the source context. We evaluate 21 frontier and open-weight models across three source domains and seven metrics. Our results reveal a consistent pattern: models achieve near-perfect schema compliance, yet the best Value Accuracy, measured by exact leaf-value match, reaches only 83.0% on text, 67.2% on images, and 23.7% on audio, where longer context makes extraction substantially harder. We release the dataset, evaluation pipeline, and all related code.

Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier scores correctness, and the analysis ends. This paradigm leaves unmeasured whether the LLM encodes any awareness of what follows the assistant response. We propose user-turn generation as a probe of this gap: given a conversation context of user query and assistant response, we let a model generate under the user role. If the model's weights encode interaction awareness, the generated user turn will be a grounded follow-up that reacts to the preceding context. Through experiments across 11 open-weight LLMs (Qwen3.5, gpt-oss, GLM) and 5 datasets (math reasoning, instruction following, conversation), we show that interaction awareness is decoupled from task accuracy. In particular, within the Qwen3.5 family, GSM8K accuracy scales from 41% (0.8B) to 96.8% (397B-A17B), yet genuine follow-up rates under deterministic generation remain near zero. In contrast, higher temperature sampling reveals interaction awareness is latent with follow up rates reaching 22%. Controlled perturbations validate that the proposed probe measures a real property of the model, and collaboration-oriented post-training on Qwen3.5-2B demonstrates an increase in follow-up rates. Our results show that user-turn generation captures a dimension of LLM behavior, interaction awareness, that is unexplored and invisible with current assistant-only benchmarks.

This study explores the performance of large language models (LLMs) in solving competitive programming problems from the Romanian Informatics Olympiad at the county level. Romania, a leading nation in computer science competitions, provides an ideal environment for evaluating LLM capabilities due to its rich history and stringent competition standards. We collected and analyzed a dataset comprising 304 challenges from 2002 to 2023, focusing on solutions written by LLMs in C++ and Python for these problems. Our primary goal is to understand why LLMs perform well or poorly on different tasks. We evaluated various models, including closed-source models like GPT-4 and open-weight models such as CodeLlama and RoMistral, using a standardized process involving multiple attempts and feedback rounds. The analysis revealed significant variations in LLM performance across different grades and problem types. Notably, GPT-4 showed strong performance, indicating its potential use as an educational tool for middle school students. We also observed differences in code quality and style across various LLMs

Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across five classification and reasoning benchmarks under five prompt variants each, measuring accuracy, token-probability calibration, verbal-confidence calibration, verbal parse rate, and prompt-perturbation spread for every (model x dataset x variant) cell. We find three broad results. First, evaluation design can materially change the conclusion. Switching Expected Calibration Error (ECE) token from a raw to a label-set-normalised definition changes per-cell calibration by a mean absolute 0.149. More strikingly, pairing a chain-of-thought prompt with a first-character evaluator on ARC-Challenge reduces apparent accuracy by 72-88% across all five primary models; two independent repair procedures recover 93.8% and 102.7% of the lost performance, indicating an evaluator-side rather than model-side failure. Second, confidence signals are fragile. On MMLU-Pro, every primary model verbally reports confidence substantially above both its accuracy and its token-probability confidence on the same rows, and verbal parse rate can collapse for a single model on a single prompt variant. Third, prompt robustness does not track parameter count reliably. Across 10 instruct models, the correlation between model size and prompt-perturbation spread ranges from -0.244 to 0.474 across benchmarks. Taken together, these results show that reliability conclusions for small language models depend not only on the model being evaluated, but also on the evaluation pipeline used to measure it. We argue that calibration definitions, evaluator logic, verbal parseability, and prompt robustness should be reported explicitly when making reliability claims.

Large Language Models (LLMs) are commonly trained on multilingual corpora that include Greek, yet reliable evaluation benchmarks for Greek-particularly those based on authentic, native-sourced content-remain limited. Existing datasets are often machine-translated from English, failing to capture Greek linguistic and cultural characteristics. We introduce GreekMMLU, a native-sourced benchmark for massive multitask language understanding in Greek, comprising 21,805 multiple-choice questions across 45 subject areas, organized under a newly defined subject taxonomy and annotated with educational difficulty levels spanning primary to professional examinations. All questions are sourced or authored in Greek from academic, professional, and governmental exams. We publicly release 16,857 samples and reserve 4,948 samples for a private leaderboard to enable robust and contamination-resistant evaluation. Evaluations of over 80 open- and closed-source LLMs reveal substantial performance gaps between frontier and open-weight models, as well as between Greek-adapted models and general multilingual ones. Finally, we provide a systematic analysis of factors influencing performance-including model scale, adaptation, and prompting-and derive insights for improving LLM capabilities in Greek.

Large language models (LLMs) have transformed NLP, yet their integration with audio remains underexplored -- despite audio's centrality to human communication. We introduce Falcon3-Audio, a family of Audio-Language Models (ALMs) built on instruction-tuned LLMs and Whisper encoders. Using a remarkably small amount of public audio data -- less than 30K hours (5K unique) -- Falcon3-Audio-7B matches the best reported performance among open-weight models on the MMAU benchmark, with a score of 64.14, matching R1-AQA, while distinguishing itself through superior data and parameter efficiency, single-stage training, and transparency. Notably, our smallest 1B model remains competitive with larger open models ranging from 2B to 13B parameters. Through extensive ablations, we find that common complexities -- such as curriculum learning, multiple audio encoders, and intricate cross-attention connectors -- are not required for strong performance, even compared to models trained on over 500K hours of data.

Instructing language models with user intent requires large instruction datasets, which are only available for a limited set of languages. In this paper, we explore alternatives to conventional instruction adaptation pipelines in low-resource scenarios. We assume a realistic scenario for low-resource languages, where only the following are available: corpora in the target language, existing open-weight multilingual base and instructed backbone LLMs, and synthetically generated instructions sampled from the instructed backbone. We present a comprehensive set of experiments for Basque that systematically study different combinations of these components evaluated on benchmarks and human preferences from 1,680 participants. Our conclusions show that target language corpora are essential, with synthetic instructions yielding robust models, and, most importantly, that using as backbone an instruction-tuned model outperforms using a base non-instructed model, and improved results when scaling up. Using Llama 3.1 instruct 70B as backbone our model comes near frontier models of much larger sizes for Basque, without using any Basque data apart from the 1.2B word corpora. We release code, models, instruction datasets, and human preferences to support full reproducibility in future research on low-resource language adaptation.

Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term "level-0" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution traces. The synthetic nature of L0-Bench enables systematic and scalable generation of test programs along various axes (e.g., number of trace steps). We evaluate a diverse array of recent closed-source and open-weight models on a baseline test set. All models exhibit degradation as the number of target trace steps increases, while larger models and reasoning-enhanced models better maintain correctness over multiple steps. Additionally, we use L0-Bench to explore test-time scaling along three dimensions: input context length, number of solutions for majority voting, and inference steps. Our results suggest substantial room to improve "level-0" reasoning and potential directions to build more reliable reasoning systems.

Foodborne gastrointestinal (GI) illness is a common cause of ill health in the UK. However, many cases do not interact with the healthcare system, posing significant challenges for traditional surveillance methods. The growth of publicly available online restaurant reviews and advancements in large language models (LLMs) present potential opportunities to extend disease surveillance by identifying public reports of GI illness. In this study, we introduce a novel annotation schema, developed with experts in GI illness, applied to the Yelp Open Dataset of reviews. Our annotations extend beyond binary disease detection, to include detailed extraction of information on symptoms and foods. We evaluate the performance of open-weight LLMs across these three tasks: GI illness detection, symptom extraction, and food extraction. We compare this performance to RoBERTa-based classification models fine-tuned specifically for these tasks. Our results show that using prompt-based approaches, LLMs achieve micro-F1 scores of over 90% for all three of our tasks. Using prompting alone, we achieve micro-F1 scores that exceed those of smaller fine-tuned models. We further demonstrate the robustness of LLMs in GI illness detection across three bias-focused experiments. Our results suggest that publicly available review text and LLMs offer substantial potential for public health surveillance of GI illness by enabling highly effective extraction of key information. While LLMs appear to exhibit minimal bias in processing, the inherent limitations of restaurant review data highlight the need for cautious interpretation of results.

Language models (LMs) have shown outstanding performance in text summarization including sensitive domains such as medicine and law. In these settings, it is important that personally identifying information (PII) included in the source document should not leak in the summary. Prior efforts have mostly focused on studying how LMs may inadvertently elicit PII from training data. However, to what extent LMs can provide privacy-preserving summaries given a non-private source document remains under-explored. In this paper, we perform a comprehensive study across two closed- and three open-weight LMs of different sizes and families. We experiment with prompting and fine-tuning strategies for privacy-preservation across a range of summarization datasets across three domains. Our extensive quantitative and qualitative analysis including human evaluation shows that LMs often cannot prevent PII leakage on their summaries and that current widely-used metrics cannot capture context dependent privacy risks.

Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community still needs to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve a total score of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play a crucial role in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.

Large Language Models (LLMs) show strong generalization across diverse tasks, yet the internal decision-making processes behind their predictions remain opaque. In this work, we study the geometry of hidden representations in LLMs through the lens of intrinsic dimension (ID), focusing specifically on decision-making dynamics in a multiple-choice question answering (MCQA) setting. We perform a large-scale study, with 28 open-weight transformer models and estimate ID across layers using multiple estimators, while also quantifying per-layer performance on MCQA tasks. Our findings reveal a consistent ID pattern across models: early layers operate on low-dimensional manifolds, middle layers expand this space, and later layers compress it again, converging to decision-relevant representations. Together, these results suggest LLMs implicitly learn to project linguistic inputs onto structured, low-dimensional manifolds aligned with task-specific decisions, providing new geometric insights into how generalization and reasoning emerge in language models.

We present EXAONE Deep series, which exhibits superior capabilities in various reasoning tasks, including math and coding benchmarks. We train our models mainly on the reasoning-specialized dataset that incorporates long streams of thought processes. Evaluation results show that our smaller models, EXAONE Deep 2.4B and 7.8B, outperform other models of comparable size, while the largest model, EXAONE Deep 32B, demonstrates competitive performance against leading open-weight models. All EXAONE Deep models are openly available for research purposes and can be downloaded from https://huggingface.co/LGAI-EXAONE

This paper introduces ExpertLongBench, an expert-level benchmark containing 11 tasks from 9 domains that reflect realistic expert workflows and applications. Beyond question answering, the application-driven tasks in ExpertLongBench demand long-form outputs that can exceed 5,000 tokens and strict adherence to domain-specific requirements. Notably, each task in ExpertLongBench includes a rubric, designed or validated by domain experts, to specify task requirements and guide output evaluation. Furthermore, we propose CLEAR, an evaluation framework that supports accurate evaluation of long-form model outputs in our benchmark. To achieve fine-grained, expert-aligned evaluation, CLEAR derives checklists from both model outputs and references by extracting information corresponding to items in the task-specific rubric. Checklist items for model outputs are then compared with corresponding items for reference outputs to assess their correctness, enabling grounded evaluation. We benchmark 11 large language models (LLMs) and analyze components in CLEAR, showing that (1) existing LLMs, with the top performer achieving only a 26.8% F1 score, require significant improvement for expert-level tasks; (2) models can generate content corresponding to the required aspects, though often not accurately; and (3) accurate checklist extraction and comparison in CLEAR can be achieved by open-weight models for more scalable and low-cost usage.

Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances.

Policy compliance assessment is a fundamental task of evaluating whether an input case strictly complies with a set of human-defined rules, more generally known as policies. In practice, human experts follow a systematic, step-by-step process to identify violations with respect to specific stipulations outlined in the policy. However, such documentation of gold-standard, expert-level reasoning processes is costly to acquire. In this paper, we introduce Policy Reasoning Traces (PRT), a form of specialized generated reasoning chains that serve as a reasoning bridge to improve an LLM's policy compliance assessment capabilities. Our empirical evaluations demonstrate that the use of PRTs for both inference-time and training-time scenarios significantly enhances the performance of open-weight and commercial models, setting a new state-of-the-art for HIPAA and GDPR policies. Beyond accuracy gains, we also highlight how PRTs can improve an LLM's ability to accurately cite policy clauses, as well as influence compliance decisions through their high utilization from the raw chains of thought.

Recent work has explored the use of large language models (LLMs) to generate tutoring responses in mathematics, yet it remains unclear how closely their instructional behavior aligns with expert human practice. We analyze a dataset of math remediation dialogues in which expert tutors, novice tutors, and seven LLMs of varying sizes, comprising both open-weight and commercial models, respond to the same student errors. We examine instructional strategies and linguistic characteristics of tutoring responses, including uptake (restating and revoicing), pressing for accuracy and reasoning, lexical diversity, readability, politeness, and agency. We find that expert tutors produce higher-quality responses than novices, and that larger LLMs generally receive higher pedagogical quality ratings than smaller models, approaching expert performance on average. However, LLMs exhibit systematic differences in their instructional profiles: they underuse discursive strategies characteristic of expert tutors while generating longer, more lexically diverse, and more polite responses. Regression analyses show that pressing for accuracy and reasoning, restating and revoicing, and lexical diversity, are positively associated with perceived pedagogical quality, whereas higher levels of agentic and polite language are negatively associated. These findings highlight the importance of analyzing instructional strategies and linguistic characteristics when evaluating tutoring responses across human tutors and intelligent tutoring systems.

Suspense is an affective response to narrative text that is believed to involve complex cognitive processes in humans. Several psychological models have been developed to describe this phenomenon and the circumstances under which text might trigger it. We replicate four seminal psychological studies of human perceptions of suspense, substituting human responses with those of different open-weight and closed-source LMs. We conclude that while LMs can distinguish whether a text is intended to induce suspense in people, LMs cannot accurately estimate the relative amount of suspense within a text sequence as compared to human judgments, nor can LMs properly capture the human perception for the rise and fall of suspense across multiple text segments. We probe the abilities of LM suspense understanding by adversarially permuting the story text to identify what cause human and LM perceptions of suspense to diverge. We conclude that, while LMs can superficially identify and track certain facets of suspense, they do not process suspense in the same way as human readers.

Commonsense intelligence in machines is often assessed by static benchmarks that compare a model's output against human-prescribed correct labels. An important, albeit implicit, assumption of these labels is that they accurately capture what any human would think, effectively treating human common sense as homogeneous. However, recent empirical work has shown that humans vary enormously in what they consider commonsensical; thus what appears self-evident to one benchmark designer may not be so to another. Here, we propose a novel method for evaluating common sense in artificial intelligence (AI), specifically in large language models (LLMs), that incorporates empirically observed heterogeneity among humans by measuring the correspondence between a model's judgment and that of a human population. We first find that, when treated as independent survey respondents, most LLMs remain below the human median in their individual commonsense competence. Second, when used as simulators of a hypothetical population, LLMs correlate with real humans only modestly in the extent to which they agree on the same set of statements. In both cases, smaller, open-weight models are surprisingly more competitive than larger, proprietary frontier models. Our evaluation framework, which ties commonsense intelligence to its cultural basis, contributes to the growing call for adapting AI models to human collectivities that possess different, often incompatible, social stocks of knowledge.

This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (\"Ust\"un et al., 2024), focusing on pairing a highly performant pre-trained model with the recently released Aya collection (Singh et al., 2024). The result is a powerful multilingual large language model serving 23 languages, expanding state-of-art language modeling capabilities to approximately half of the world's population. The Aya model covered 101 languages whereas Aya 23 is an experiment in depth vs breadth, exploring the impact of allocating more capacity to fewer languages that are included during pre-training. Aya 23 outperforms both previous massively multilingual models like Aya 101 for the languages it covers, as well as widely used models like Gemma, Mistral and Mixtral on an extensive range of discriminative and generative tasks. We release the open weights for both the 8B and 35B models as part of our continued commitment for expanding access to multilingual progress.

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for helpfulness, exposure to user information, emotional and subjective dialogue, and debugging code printing internal variables, among others. Fine-tuned models lose their ability to reason about contextual privacy norms, share information inappropriately with tools, and violate memory boundaries across contexts. Privacy collapse is a ``silent failure'' because models maintain high performance on standard safety and utility benchmarks whilst exhibiting severe privacy vulnerabilities. Our experiments show evidence of privacy collapse across six models (closed and open weight), five fine-tuning datasets (real-world and controlled data), and two task categories (agentic and memory-based). Our mechanistic analysis reveals that privacy representations are uniquely fragile to fine-tuning, compared to task-relevant features which are preserved. Our results reveal a critical gap in current safety evaluations, in particular for the deployment of specialised agents.

As large language models (LLMs) increasingly interact with external tools, reward modeling for tool use has become a critical yet underexplored area. Existing reward models, trained primarily on natural language outputs, struggle to evaluate tool-based reasoning and execution. To quantify this gap, we introduce FC-RewardBench, the first benchmark designed to systematically assess reward models' performance in tool-calling scenarios. Our analysis shows that current reward models often miss key signals of effective tool use, highlighting the need for domain-specific modeling. To address this, we propose a training framework for outcome-based reward models using data synthesized from permissively licensed, open-weight LLMs. We train models ranging from 1.7B to 14B parameters and evaluate them across seven out-of-domain benchmarks. These models consistently outperform general-purpose baselines, achieving up to 25\% average improvement in downstream task performance and enabling data-efficient fine-tuning through reward-guided filtering.

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

Can language models (LMs) self-refine their own responses? This question is increasingly relevant as a wide range of real-world user interactions involve refinement requests. However, prior studies have largely tested LMs' refinement abilities on verifiable tasks such as competition math or symbolic reasoning with simplified scaffolds, whereas users often pose open-ended queries and provide varying degrees of feedback on what they desire. The recent advent of reasoning models that exhibit self-reflection patterns in their chains-of-thought further motivates this question. To analyze this, we introduce RefineBench, a benchmark of 1,000 challenging problems across 11 domains paired with a checklist-based evaluation framework. We evaluate two refinement modes: (1) guided refinement, where an LM is provided natural language feedback, and (2) self-refinement, where LMs attempt to improve without guidance. In the self-refinement setting, even frontier LMs such as Gemini 2.5 Pro and GPT-5 achieve modest baseline scores of 31.3% and 29.1%, respectively, and most models fail to consistently improve across iterations (e.g., Gemini-2.5-Pro gains only +1.8%, while DeepSeek-R1 declines by -0.1%). By contrast, in guided refinement, both proprietary LMs and large open-weight LMs (>70B) can leverage targeted feedback to refine responses to near-perfect levels within five turns. These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses, and that RefineBench provides a valuable testbed for tracking progress.

Large language models (LLMs) have shown strong performance in many reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of the leading causes for such performance. LLMs, in fact, are susceptible to content variations, demonstrating a lack of robust planning or symbolic abstractions supporting their reasoning process. To improve reliability, many attempts have been made to combine LLMs with symbolic methods. Nevertheless, existing approaches fail to effectively leverage symbolic representations due to the challenges involved in developing reliable and scalable verification mechanisms. In this paper, we propose to overcome such limitations by synthesizing high-quality symbolic reasoning trajectories with stepwise pseudo-labels at scale via Monte Carlo estimation. A Process Reward Model (PRM) can be efficiently trained based on the synthesized data and then used to select more symbolic trajectories. The trajectories are then employed with Direct Preference Optimization (DPO) and Supervised Fine-Tuning (SFT) to improve logical reasoning and generalization. Our results on benchmarks (i.e., FOLIO and LogicAsker) show the effectiveness of the proposed method with gains on frontier and open-weight models. Moreover, additional experiments on claim verification data reveal that fine-tuning on the generated symbolic reasoning trajectories enhances out-of-domain generalizability, suggesting the potential impact of the proposed method in enhancing planning and logical reasoning.

Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We introduce LongProc (Long Procedural Generation), a new benchmark that requires both the integration of highly dispersed information and long-form generation. LongProc consists of six diverse procedural generation tasks, such as extracting structured information from HTML pages into a TSV format and executing complex search procedures to create travel plans. These tasks challenge LCLMs by testing their ability to follow detailed procedural instructions, synthesize and reason over dispersed information, and generate structured, long-form outputs (up to 8K tokens). Furthermore, as these tasks adhere to deterministic procedures and yield structured outputs, they enable reliable rule-based evaluation. We evaluate 17 LCLMs on LongProc across three difficulty levels, with maximum numbers of output tokens set at 500, 2K, and 8K. Notably, while all tested models claim a context window size above 32K tokens, open-weight models typically falter on 2K-token tasks, and closed-source models like GPT-4o show significant degradation on 8K-token tasks. Further analysis reveals that LCLMs struggle to maintain long-range coherence in long-form generations. These findings highlight critical limitations in current LCLMs and suggest substantial room for improvement. Data and code available at: https://princeton-pli.github.io/LongProc

Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generating statements they believe are false. However, these techniques are typically validated in narrow settings that do not capture the diverse lies LLMs can generate. We introduce LIARS' BENCH, a testbed consisting of 72,863 examples of lies and honest responses generated by four open-weight models across seven datasets. Our settings capture qualitatively different types of lies and vary along two dimensions: the model's reason for lying and the object of belief targeted by the lie. Evaluating three black- and white-box lie detection techniques on LIARS' BENCH, we find that existing techniques systematically fail to identify certain types of lies, especially in settings where it's not possible to determine whether the model lied from the transcript alone. Overall, LIARS' BENCH reveals limitations in prior techniques and provides a practical testbed for guiding progress in lie detection.

Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, models risk generating stereotyped, insensitive, or misleading responses that fail to reflect cultural diversity w.r.t Helpful, Harmless, and Honest (HHH) paradigm. Existing benchmarks represent early steps toward cultural alignment; yet, no benchmarks currently enables systematic evaluation of cultural alignment in line with UNESCO's principles of cultural diversity w.r.t HHH paradigm. Therefore, to address this gap, we built Align-Cultura, two-stage pipeline for cultural alignment. Stage I constructs CULTURAX, the HHH-English dataset grounded in the UNESCO cultural taxonomy, through Query Construction, which reclassifies prompts, expands underrepresented domains (or labels), and prevents data leakage with SimHash. Then, Response Generation pairs prompts with culturally grounded responses via two-stage rejection sampling. The final dataset contains 1,500 samples spanning 30 subdomains of tangible and intangible cultural forms. Stage II benchmarks CULTURAX on general-purpose models, culturally fine-tuned models, and open-weight LLMs (Qwen3-8B and DeepSeek-R1-Distill-Qwen-7B). Empirically, culturally fine-tuned models improve joint HHH by 4%-6%, reduce cultural failures by 18%, achieve 10%-12% efficiency gains, and limit leakage to 0.3%.

Large language models (LLMs) are becoming increasingly proficient in processing and generating multilingual texts, which allows them to address real-world problems more effectively. However, language understanding is a far more complex issue that goes beyond simple text analysis. It requires familiarity with cultural context, including references to everyday life, historical events, traditions, folklore, literature, and pop culture. A lack of such knowledge can lead to misinterpretations and subtle, hard-to-detect errors. To examine language models' knowledge of the Polish cultural context, we introduce the Polish linguistic and cultural competency benchmark, consisting of 600 manually crafted questions. The benchmark is divided into six categories: history, geography, culture & tradition, art & entertainment, grammar, and vocabulary. As part of our study, we conduct an extensive evaluation involving over 30 open-weight and commercial LLMs. Our experiments provide a new perspective on Polish competencies in language models, moving past traditional natural language processing tasks and general knowledge assessment.

Large Language Models (LLMs) solely trained on next-token prediction learn to solve a wide range of problems involving mathematical reasoning. But how does this ability evolve during training? We show the first analysis of how mathematical reasoning abilities of several open-weight LLMs develop during pre-training and post-training. To this end, we construct MathCAMPS, a synthetic dataset of novel mathematical reasoning problems grounded in 44 fine-grained skills taken from the Common Core curriculum from K to 8th grades. In one experiment, we show that mathematical skills are learned during pre-training in an order that measurably correlates with the human-designed curriculum, even though training data are randomly ordered. We also show a detailed analysis of which mathematical abilities benefit from instruction tuning, a widely used post-training method and, in contrast, which skills suffer. Our work paves the way for an empirical understanding of LLM training dynamics in relation to reasoning.

Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embedded systems programming. This domain involves hardware register manipulation, vendor-specific SDKs, real-time operating system APIs, and hardware abstraction layers that are underrepresented in standard pretraining corpora. We introduce H2LooP Spark Preview, a continual pretraining (CPT) pipeline that adapts the OLMo-3-7B-a fully open language model to the embedded systems domain using BF16 LoRA with rank-stabilized scaling on 8 NVIDIA H100 GPUs. Our training corpus is constructed from repository-datasheet pairs covering 100B tokens of raw embedded systems data across 117 manufacturers, processed using the hierarchical datasheet-to-code mapping approach proposed in SpecMap (Nipane et al., 2026). The resulting curated dataset split contains 23.5B tokens across 13 embedded domains. Continual pretraining with high-rank LoRA (r=512) yields substantial gains, reducing in-domain perplexity by 70.4% and held-out repository perplexity by 66.1%. On generative code completion benchmarks spanning 13 embedded domains, our 7B model outperforms Claude Opus 4.6 and Qwen3-Coder-30B on 8 categories in token accuracy, showing that targeted continual pretraining enables smaller open-weight models to rival frontier systems on specialized technical tasks. We release the production training checkpoint on Huggingface as an open-source artifact.

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which may be more easily interpretable. However, these SAEs can have millions of distinct latent features, making it infeasible for humans to manually interpret each one. In this work, we build an open-source automated pipeline to generate and evaluate natural language explanations for SAE features using LLMs. We test our framework on SAEs of varying sizes, activation functions, and losses, trained on two different open-weight LLMs. We introduce five new techniques to score the quality of explanations that are cheaper to run than the previous state of the art. One of these techniques, intervention scoring, evaluates the interpretability of the effects of intervening on a feature, which we find explains features that are not recalled by existing methods. We propose guidelines for generating better explanations that remain valid for a broader set of activating contexts, and discuss pitfalls with existing scoring techniques. We use our explanations to measure the semantic similarity of independently trained SAEs, and find that SAEs trained on nearby layers of the residual stream are highly similar. Our large-scale analysis confirms that SAE latents are indeed much more interpretable than neurons, even when neurons are sparsified using top-k postprocessing. Our code is available at https://github.com/EleutherAI/sae-auto-interp, and our explanations are available at https://huggingface.co/datasets/EleutherAI/auto_interp_explanations.

Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavour that requires a deep assessment of LLMs' outputs. Existing methods and benchmarks rely primarily on automated metrics and static analysis tools, which often fail to capture the nuances of user instructions and LLM outputs. To address this gap, we propose using the LLM-as-a-Judge methodology to evaluate the alignment of LLMs with coding preferences. Based on this approach, we present CodeUltraFeedback, a comprehensive dataset designed to facilitate the evaluation and improvement of LLM alignment. CodeUltraFeedback consists of 10,000 coding instructions, each annotated with four responses generated from a diverse pool of 14 LLMs. These responses are ranked based on five distinct coding preferences using GPT-3.5 as a judge, providing both numerical scores and detailed textual feedback. Our analysis of CodeUltraFeedback reveals that responses from GPT-3.5 and GPT-4 are generally preferred over those from open-weight LLMs, highlighting significant differences in alignment between closed and open-weight models. In turn, we explore the usage of CodeUltraFeedback as feedback data to fine-tune and align CodeLlama-7B-Instruct using supervised fine-tuning (SFT) and reinforcement learning from AI feedback (RLAIF) with direct preference optimization (DPO). The resulting aligned CodeLlama-7B-Instruct model outperforms larger LLMs in terms of alignment with coding preferences and shows improved functional correctness on the HumanEval+ benchmark compared to the original instruct model. Therefore, our contributions bridge the gap in preference tuning of LLMs for code and set the stage for further advancements in model alignment and RLAIF in automated software engineering.

Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic interpretability analysis of verbalized confidence, using linear probes and contrastive activation addition (CAA) steering to show that calibration and verbalized confidence signals are encoded linearly but are orthogonal to one another -- a finding consistent across three open-weight models and four datasets. Interestingly, when models are prompted to simultaneously reason through a problem and verbalize a confidence score, the reasoning process disrupts the verbalized confidence direction, exacerbating miscalibration. We term this the "Reasoning Contamination Effect." Leveraging this insight, we introduce a two-stage adaptive steering pipeline that reads the model's internal accuracy estimate and steers verbalized output to match it, substantially improving calibration alignment across all evaluated models.

This paper introduces the "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset, designed to evaluate the social and cultural variation of Large Language Models (LLMs) across multiple languages and value-sensitive topics. We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy. CIVICS is designed to generate responses showing LLMs' encoded and implicit values. Through our dynamic annotation processes, tailored prompt design, and experiments, we investigate how open-weight LLMs respond to value-sensitive issues, exploring their behavior across diverse linguistic and cultural contexts. Using two experimental set-ups based on log-probabilities and long-form responses, we show social and cultural variability across different LLMs. Specifically, experiments involving long-form responses demonstrate that refusals are triggered disparately across models, but consistently and more frequently in English or translated statements. Moreover, specific topics and sources lead to more pronounced differences across model answers, particularly on immigration, LGBTQI rights, and social welfare. As shown by our experiments, the CIVICS dataset aims to serve as a tool for future research, promoting reproducibility and transparency across broader linguistic settings, and furthering the development of AI technologies that respect and reflect global cultural diversities and value pluralism. The CIVICS dataset and tools will be made available upon publication under open licenses; an anonymized version is currently available at https://huggingface.co/CIVICS-dataset.

Large language models (LLMs) can reliably distinguish grammatical from ungrammatical sentences, but how grammatical knowledge is represented within the models remains an open question. We investigate whether different syntactic phenomena recruit shared or distinct components in LLMs. Using a functional localization approach inspired by cognitive neuroscience, we identify the LLM units most responsive to 67 English syntactic phenomena in seven open-weight models. These units are consistently recruited across sentences containing the phenomena and causally support the models' syntactic performance. Critically, different types of syntactic agreement (e.g., subject-verb, anaphor, determiner-noun) recruit overlapping sets of units, suggesting that agreement constitutes a meaningful functional category for LLMs. This pattern holds in English, Russian, and Chinese; and further, in a cross-lingual analysis of 57 diverse languages, structurally more similar languages share more units for subject-verb agreement. Taken together, these findings reveal that syntactic agreement-a critical marker of syntactic dependencies-constitutes a meaningful category within LLMs' representational spaces.

Synthetic long-context LLM benchmarks (e.g., "needle-in-the-haystack") test only surface-level retrieval capabilities, but how well can long-context LLMs retrieve, synthesize, and reason over information across book-length inputs? We address this question by creating NoCha, a dataset of 1,001 minimally different pairs of true and false claims about 67 recently-published English fictional books, written by human readers of those books. In contrast to existing long-context benchmarks, our annotators confirm that the largest share of pairs in NoCha require global reasoning over the entire book to verify. Our experiments show that while human readers easily perform this task, it is enormously challenging for all ten long-context LLMs that we evaluate: no open-weight model performs above random chance (despite their strong performance on synthetic benchmarks), while GPT-4o achieves the highest accuracy at 55.8%. Further analysis reveals that (1) on average, models perform much better on pairs that require only sentence-level retrieval vs. global reasoning; (2) model-generated explanations for their decisions are often inaccurate even for correctly-labeled claims; and (3) models perform substantially worse on speculative fiction books that contain extensive world-building. The methodology proposed in NoCha allows for the evolution of the benchmark dataset and the easy analysis of future models.

Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the advantages reported for settings where all merged experts have distinct roles and are tuned on clearly separated tasks also hold in settings where the merged experts do not have clearly distinct roles, but are trained on overlapping or even conflicting objectives. To evaluate this setting, we present a large-scale, systematic evaluation of "in-the-wild" model merging of heterogeneous experts, that may have been trained on overlapping or conflicting objectives. Concretely, we evaluate six state-of-the-art merging methods, including recent subspace methods, across four open-weight LLMs, twelve fine-tuned checkpoints per base model, and sixteen standard LLM benchmarks. Evaluating through standardized benchmarks, we measure both the probability that a model merged from a heterogeneous set of experts outperforms the base model and we measure relative gains over the best individual checkpoint. Our results show that the oldest and simplest method, Task Arithmetic, is the only approach that reliably yields performance gains on LLMs in this "in-the-wild" setting. Other interference-aware and subspace merging methods typically do not result in notable improvements over the base model. Our findings indicate that current merging techniques mostly do not enable extracting useful weight updates from heterogeneous and potentially conflicting versions. This motivates the design of LLM-specific merging algorithms and merging-aware fine-tuning methods.

Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of high- and mid-resource scripts. We introduce GlotOCR Bench, a comprehensive benchmark evaluating OCR generalization across 100+ Unicode scripts. Our benchmark comprises clean and degraded image variants rendered from real multilingual texts. Images are rendered using fonts from the Google Fonts repository, shaped with HarfBuzz and rasterized with FreeType, supporting both LTR and RTL scripts. Samples of rendered images were manually reviewed to verify correct rendering across all scripts. We evaluate a broad suite of open-weight and proprietary vision-language models and find that most perform well on fewer than ten scripts, and even the strongest frontier models fail to generalize beyond thirty scripts. Performance broadly tracks script-level pretraining coverage, suggesting that current OCR systems rely on language model pretraining as much as on visual recognition. Models confronted with unfamiliar scripts either produce random noise or hallucinate characters from similar scripts they already know. We release the benchmark and pipeline for reproducibility. Pipeline Code: https://github.com/cisnlp/glotocr-bench, Benchmark: https://hf.co/datasets/cis-lmu/glotocr-bench.

Gender-neutral rewriting (GNR) aims to reformulate text to eliminate unnecessary gender specifications while preserving meaning, a particularly challenging task in grammatical-gender languages like Italian. In this work, we conduct the first systematic evaluation of state-of-the-art large language models (LLMs) for Italian GNR, introducing a two-dimensional framework that measures both neutrality and semantic fidelity to the input. We compare few-shot prompting across multiple LLMs, fine-tune selected models, and apply targeted cleaning to boost task relevance. Our findings show that open-weight LLMs outperform the only existing model dedicated to GNR in Italian, whereas our fine-tuned models match or exceed the best open-weight LLM's performance at a fraction of its size. Finally, we discuss the trade-off between optimizing the training data for neutrality and meaning preservation.

This paper presents FormationEval, an open multiple-choice question benchmark for evaluating language models on petroleum geoscience and subsurface disciplines. The dataset contains 505 questions across seven domains including petrophysics, petroleum geology and reservoir engineering, derived from three authoritative sources using a reasoning model with detailed instructions and a concept-based approach that avoids verbatim copying of copyrighted text. Each question includes source metadata to support traceability and audit. The evaluation covers 72 models from major providers including OpenAI, Anthropic, Google, Meta and open-weight alternatives. The top performers achieve over 97\% accuracy, with Gemini 3 Pro Preview reaching 99.8\%, while tier and domain gaps persist. Among open-weight models, GLM-4.7 leads at 98.6\%, with several DeepSeek, Llama, Qwen and Mistral models also exceeding 93\%. The performance gap between open-weight and closed models is narrower than expected, with several lower-cost open-weight models exceeding 90\% accuracy. Petrophysics emerges as the most challenging domain across all models, while smaller models show wider performance variance. Residual length bias in the dataset (correct answers tend to be longer) is documented along with bias mitigation strategies applied during construction. The benchmark, evaluation code and results are publicly available.

Africa is home to over one-third of the world's languages, yet remains underrepresented in AI research. We introduce Afri-MCQA, the first Multilingual Cultural Question-Answering benchmark covering 7.5k Q&A pairs across 15 African languages from 12 countries. The benchmark offers parallel English-African language Q&A pairs across text and speech modalities and was entirely created by native speakers. Benchmarking large language models (LLMs) on Afri-MCQA shows that open-weight models perform poorly across evaluated cultures, with near-zero accuracy on open-ended VQA when queried in native language or speech. To evaluate linguistic competence, we include control experiments meant to assess this specific aspect separate from cultural knowledge, and we observe significant performance gaps between native languages and English for both text and speech. These findings underscore the need for speech-first approaches, culturally grounded pretraining, and cross-lingual cultural transfer. To support more inclusive multimodal AI development in African languages, we release our Afri-MCQA under academic license or CC BY-NC 4.0 on HuggingFace (https://huggingface.co/datasets/Atnafu/Afri-MCQA)

Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies without explicitly modeling the supporting evidence found in scientific literature. We introduce PlantMarkerBench, a multi-species benchmark for evaluating literature-grounded plant marker evidence interpretation from full-text biological papers. PlantMarkerBench is constructed using a modular curation pipeline integrating large-scale literature retrieval, hybrid search, species-aware biological grounding, structured evidence extraction, and targeted human review. The benchmark spans four plant species -- Arabidopsis, maize, rice, and tomato -- and contains 5,550 sentence-level evidence instances annotated for marker-evidence validity, evidence type, and support strength. We define two benchmark tasks: determining whether a candidate sentence provides valid marker evidence for a gene-cell-type pair, and classifying the evidence into expression, localization, function, indirect, or negative categories. We benchmark diverse open-weight and closed-source language models across species and prompting strategies. Although frontier models achieve relatively strong performance on direct expression evidence, performance drops substantially on functional, indirect, and weak-support evidence, with evidence-type confusion emerging as a dominant failure mode. Open-weight models additionally exhibit elevated false-positive rates under ambiguous biological contexts. PlantMarkerBench provides a challenging and reproducible evaluation framework for literature-grounded biological evidence attribution and supports future research on trustworthy scientific information extraction and AI-assisted plant biology.

Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce \texttt{RealChart2Code}, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement in a multi-turn conversational setting. Our comprehensive evaluation of 14 leading VLMs on RealChart2Code reveals significant performance degradation compared to simpler benchmarks, highlighting their struggles with complex plot structures and authentic data. Our analysis uncovers a substantial performance gap between proprietary and open-weight models and confirms that even state-of-the-art VLMs often fail to accurately replicate intricate, multi-panel charts. These findings provide valuable insights into the current limitations of VLMs and guide future research directions. We release the benchmark and code at https://github.com/Speakn0w/RealChart2Code.

Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and short-form question-answering. However, many real-world applications require evaluating LLMs in processing professional documents, synthesizing information, and generating comprehensive reports in response to user queries. We introduce ProfBench: a set of over 7000 response-criterion pairs as evaluated by human-experts with professional knowledge across Physics PhD, Chemistry PhD, Finance MBA and Consulting MBA. We build robust and affordable LLM-Judges to evaluate ProfBench rubrics, by mitigating self-enhancement bias and reducing the cost of evaluation by 2-3 orders of magnitude, to make it fair and accessible to the broader community. Our findings reveal that ProfBench poses significant challenges even for state-of-the-art LLMs, with top-performing models like GPT-5-high achieving only 65.9\% overall performance. Furthermore, we identify notable performance disparities between proprietary and open-weight models and provide insights into the role that extended thinking plays in addressing complex, professional-domain tasks. Data: https://huggingface.co/datasets/nvidia/ProfBench and Code: https://github.com/NVlabs/ProfBench

LLMs are ubiquitous in modern NLP, and while their applicability extends to texts produced for democratic activities such as online deliberations or large-scale citizen consultations, ethical questions have been raised for their usage as analysis tools. We continue this line of research with two main goals: (a) to develop resources that can help standardize citizen contributions in public forums at the pragmatic level, and make them easier to use in topic modeling and political analysis; (b) to study how well this standardization can reliably be performed by small, open-weights LLMs, i.e. models that can be run locally and transparently with limited resources. Accordingly, we introduce Corpus Clarification as a preprocessing framework for large-scale consultation data that transforms noisy, multi-topic contributions into structured, self-contained argumentative units ready for downstream analysis. We present GDN-CC, a manually-curated dataset of 1,231 contributions to the French Grand Débat National, comprising 2,285 argumentative units annotated for argumentative structure and manually clarified. We then show that finetuned Small Language Models match or outperform LLMs on reproducing these annotations, and measure their usability for an opinion clustering task. We finally release GDN-CC-large, an automatically annotated corpus of 240k contributions, the largest annotated democratic consultation dataset to date.

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their underlying reasoning processes remain highly overfit to standard textual formatting. We propose a perturbation pipeline consisting of 14 techniques to evaluate robustness of LLM reasoning. We apply this pipeline to AIME 2024 dataset and evalute 8 state-of-the-art models on the resulting benchmark. While frontier models exhibit resilience, open weights reasoning models suffer catastrophic collapses (up to 55% average accuracy drops across perturbations and up to 100% on some), exposing structural fragility. To further disentangle mechanical parsing failures from downstream reasoning failures, we strictly isolate the models' working memory capacity by forcing models to solve multiple unperturbed mathematical problems sequentially within a single context window. Our results indicate that open weight models ranging from 7B to 120B parameters and Claude Opus 4.6 exhibit accuracy decay on subsequent problems. This degradation demonstrates that intermediate reasoning steps permanently pollute standard dense attention mechanisms. We argue that to achieve reliable reasoning, future reasoning architectures must integrate explicit contextual resets within a model's own Chain-of-Thought, leading to fundamental open questions regarding the optimal granularity of atomic reasoning tasks.

Generative AI release decisions determine whether system components are made available, but release does not address many other elements that change how users and stakeholders are able to engage with a system. Beyond release, access to system components informs potential risks and benefits. Access refers to practical needs, infrastructurally, technically, and societally, in order to use available components in some way. We deconstruct access along three axes: resourcing, technical usability, and utility. Within each category, a set of variables per system component clarify tradeoffs. For example, resourcing requires access to computing infrastructure to serve model weights. We also compare the accessibility of four high performance language models, two open-weight and two closed-weight, showing similar considerations for all based instead on access variables. Access variables set the foundation for being able to scale or increase access to users; we examine the scale of access and how scale affects ability to manage and intervene on risks. This framework better encompasses the landscape and risk-benefit tradeoffs of system releases to inform system release decisions, research, and policy.

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of instruction-following tasks, yet their grasp of nuanced social science concepts remains underexplored. This paper examines whether LLMs can identify and classify fine-grained forms of populism, a complex and contested concept in both academic and media debates. To this end, we curate and release novel datasets specifically designed to capture populist discourse. We evaluate a range of pre-trained (large) language models, both open-weight and proprietary, across multiple prompting paradigms. Our analysis reveals notable variation in performance, highlighting the limitations of LLMs in detecting populist discourse. We find that a fine-tuned RoBERTa classifier vastly outperforms all new-era instruction-tuned LLMs, unless fine-tuned. Additionally, we apply our best-performing model to analyze campaign speeches by Donald Trump, extracting valuable insights into his strategic use of populist rhetoric. Finally, we assess the generalizability of these models by benchmarking them on campaign speeches by European politicians, offering a lens into cross-context transferability in political discourse analysis. In this setting, we find that instruction-tuned LLMs exhibit greater robustness on out-of-domain data.

Unlimited, or so-called helpful-only language models are trained without safety alignment constraints and never refuse user queries. They are widely used by leading AI companies as internal tools for red teaming and alignment evaluation. For example, if a safety-aligned model produces harmful outputs similar to an unlimited model, this indicates alignment failures that require further attention. Despite their essential role in assessing alignment, such models are not available to the research community. We introduce Jinx, a helpful-only variant of popular open-weight LLMs. Jinx responds to all queries without refusals or safety filtering, while preserving the base model's capabilities in reasoning and instruction following. It provides researchers with an accessible tool for probing alignment failures, evaluating safety boundaries, and systematically studying failure modes in language model safety.

We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require models to generate and utilize intermediate images - such as sketches, structural diagrams, or path drawings - to guide their reasoning process. This setup closely mirrors how humans solve complex problems through "drawing to think". To solve this, MIRA focuses on tasks that are intrinsically challenging and involve complex structures, spatial relationships, or reasoning steps that are difficult to express through language alone. To ensure that our evaluation data is of high-quality, we include 546 multimodal problems, annotated with intermediate visual images and final answers. We also propose a unified evaluation protocol for MIRA that spans three levels of evaluation input: direct input with image and question only, text-only CoT input with image and thinking prompts, and Visual-CoT input with both annotated image clues and textual thinking prompts. To probe the upper bound of model capacity on our benchmark, we also report pass@k and majority voting accuracies under different k settings. Experimental results show that existing multimodal large language models, including strongest private models as well as strong open-weight models, perform poorly when relying solely on textual prompts. However, when intermediate visual cues are provided, model performance improves consistently, yielding an average relative gain of 33.7% across all models and tasks. We also probe the upper bound by expanding the search space and designing textual prompts aligned with Visual-CoT, but both yield only limited improvements compared to our Visual-CoT setting. These results underscore the critical role of imagined visual information in enabling successful reasoning on MIRA.

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We study political censorship in Chinese-origin language models as a natural experiment, using probes, surgical ablations, and behavioral tests across nine open-weight models from five labs. Three findings follow. First, probe accuracy alone is non-diagnostic: political probes, null controls, and permutation baselines can all reach 100%, so held-out category generalization is the informative test. Second, surgical ablation reveals lab-specific routing. Removing the political-sensitivity direction eliminates censorship and restores accurate factual output in most models tested, while one model confabulates because its architecture entangles factual knowledge with the censorship mechanism. Cross-model transfer fails, indicating that routing geometry is model- and lab-specific. Third, refusal is no longer the dominant censorship mechanism. Within one model family, hard refusal falls to zero while narrative steering rises to the maximum, making censorship invisible to refusal-only benchmarks. These results support a three-stage descriptive framework: detect, route, generate. Models often retain the relevant knowledge; alignment changes how that knowledge is expressed. Evaluations that audit only detection or refusal therefore miss the routing mechanism that most directly determines behavior.

Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular form. Previous approaches demonstrated notable performance by leveraging either closed-source large language models (LLMs) or fine-tuned open-weight LLMs. However, fine-tuning LLMs requires high-quality training data, which is costly to obtain, and utilizing closed-source LLMs poses accessibility challenges and leads to reproducibility issues. In this paper, we propose Multi-Agent Collaboration with Tool use (MACT), a framework that requires neither closed-source models nor fine-tuning. In MACT, a planning agent and a coding agent that also make use of tools collaborate to answer questions. Our experiments on four TQA benchmarks show that MACT outperforms previous SoTA systems on three out of four benchmarks and that it performs comparably to the larger and more expensive closed-source model GPT-4 on two benchmarks, even when using only open-weight models without any fine-tuning. We conduct extensive analyses to prove the effectiveness of MACT's multi-agent collaboration in TQA.

We introduce Motif-2-12.7B, a new open-weight foundation model that pushes the efficiency frontier of large language models by combining architectural innovation with system-level optimization. Designed for scalable language understanding and robust instruction generalization under constrained compute budgets, Motif-2-12.7B builds upon Motif-2.6B with the integration of Grouped Differential Attention (GDA), which improves representational efficiency by disentangling signal and noise-control attention pathways. The model is pre-trained on 5.5 trillion tokens spanning diverse linguistic, mathematical, scientific, and programming domains using a curriculum-driven data scheduler that gradually changes the data composition ratio. The training system leverages the MuonClip optimizer alongside custom high-performance kernels, including fused PolyNorm activations and the Parallel Muon algorithm, yielding significant throughput and memory efficiency gains in large-scale distributed environments. Post-training employs a three-stage supervised fine-tuning pipeline that successively enhances general instruction adherence, compositional understanding, and linguistic precision. Motif-2-12.7B demonstrates competitive performance across diverse benchmarks, showing that thoughtful architectural scaling and optimized training design can rival the capabilities of much larger models.

We present ACADATA, a high-quality parallel dataset for academic translation, that consists of two subsets: ACAD-TRAIN, which contains approximately 1.5 million author-generated paragraph pairs across 96 language directions and ACAD-BENCH, a curated evaluation set of almost 6,000 translations covering 12 directions. To validate its utility, we fine-tune two Large Language Models (LLMs) on ACAD-TRAIN and benchmark them on ACAD-BENCH against specialized machine-translation systems, general-purpose, open-weight LLMs, and several large-scale proprietary models. Experimental results demonstrate that fine-tuning on ACAD-TRAIN leads to improvements in academic translation quality by +6.1 and +12.4 d-BLEU points on average for 7B and 2B models respectively, while also improving long-context translation in a general domain by up to 24.9% when translating out of English. The fine-tuned top-performing model surpasses the best propietary and open-weight models on academic translation domain. By releasing ACAD-TRAIN, ACAD-BENCH and the fine-tuned models, we provide the community with a valuable resource to advance research in academic domain and long-context translation.