Related papers: When Models Ignore Definitions: Measuring Semantic…

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Large language models (LLMs) with extended context windows show promise for complex legal reasoning tasks, yet their ability to understand long legal documents remains insufficiently evaluated. Developing long-context benchmarks that…

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

We present an empirical evaluation of Large Language Models in code understanding associated with non-trivial, semantic-preserving program transformations such as copy propagation or constant folding. Our findings show that LLMs fail to…

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Logical reasoning is a core capability for large language models (LLMs), yet existing benchmarks that rely solely on final-answer accuracy fail to capture the quality of the reasoning process. To address this, we introduce FineLogic, a…

Multimodal Large Language Models (MLLMs) are set to transform how machines process and generate human-like responses by integrating diverse modalities such as text, images, and code. Yet, effectively harnessing their capabilities hinges on…

This paper introduces MMRefine, a MultiModal Refinement benchmark designed to evaluate the error refinement capabilities of Multimodal Large Language Models (MLLMs). As the emphasis shifts toward enhancing reasoning during inference,…

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains questionable. In this paper, we identify a critical failure…

The cognitive mechanism by which Large Language Models (LLMs) solve mathematical problems remains a widely debated and unresolved issue. Currently, there is little interpretable experimental evidence that connects LLMs' problem-solving with…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

People use large language models (LLMs) when they should not. This is partly because they see LLMs compose poems and answer intricate questions, so they understandably, but incorrectly, assume LLMs won't stumble on basic tasks like simple…

Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual…

Large Language Models (LLMs) often lack meaningful confidence estimates for their outputs. While base LLMs are known to exhibit next-token calibration, it remains unclear whether they can assess confidence in the actual meaning of their…

The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an…

To reduce issues like hallucinations and lack of control in Large Language Models (LLMs), a common method is to generate responses by grounding on external contexts given as input, known as knowledge-augmented models. However, previous…

Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest that this prowess is…

Recent work shows that fine-tuned Large Language Models (LLMs) can achieve high valid plan rates on PDDL planning tasks. However, it remains unclear whether this reflects transferable planning competence or domain-specific memorization. In…