Related papers: ReCrit: Transition-Aware Reinforcement Learning fo…

Reinforcement Learning (RL)-based post-training has significantly advanced the complex reasoning capabilities of language models, fostering sophisticated self-reflection processes. However, this ``slow thinking'' paradigm presents a…

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…

Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Access to the right evidence does not guarantee that large language models (LLMs) will reason with it correctly. This gap between retrieval and reasoning is especially concerning in clinical settings, where outputs must align with…

Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of "thinking" tokens before the main output, either always enabled or externally toggled at inference time. Although this can help on…

Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they are actually rewarding. In this paper we develop…

Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code representations shift. While continual learning…

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…

The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp…

Large language models (LLMs) achieve high performance on mathematical reasoning, but these results can be inflated by training data leakage or superficial pattern matching rather than genuine reasoning. To this end, an adversarial…

Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate queries, and search again. Training such agents raises a credit-assignment challenge:…

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…

Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic…

The most dangerous error in clinical trial interpretation is equating p > 0.05 with no effect. This review provides a practical, algorithm-based framework for classifying randomized controlled trial (RCT) results into six distinct…

A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language. To address this challenge in science communication, we introduce a reinforcement…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…