Related papers: Training Language Model to Critique for Better Ref…

Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that…

The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark…

Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose…

Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context reward hacking (ICRH), a phenomenon where LLMs iteratively optimize their behavior to…

Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Recent advancements in large language models (LLMs) have demonstrated that progressive refinement, rather than providing a single answer, results in more accurate and thoughtful outputs. However, existing methods often rely heavily on…

Despite significant advancements in multimodal reasoning tasks, existing Large Vision-Language Models (LVLMs) are prone to producing visually ungrounded responses when interpreting associated images. In contrast, when humans embark on…

Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…

Current large language models (LLMs), even those explicitly trained for reasoning, often struggle with ambiguous content moderation cases due to misleading "decision shortcuts" embedded in context. Inspired by cognitive psychology insights…

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Feedback is crucial for every design process, such as user interface (UI) design, and automating design critiques can significantly improve the efficiency of the design workflow. Although existing multimodal large language models (LLMs)…

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Large language models (LLMs) have been widely adopted in mathematical optimization in scientific scenarios for their extensive knowledge and advanced reasoning capabilities. Existing methods mainly focus on utilizing LLMs to solve…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…

Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely on human supervision or parameter retraining, both of which…

Large Language Models (LLMs) show strong potential for automating model generation from natural-language descriptions. A common approach begins with an initial model generation, followed by an iterative critique-refine loop in which the…