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 designed to assess LLMs' abilities to critique and rectify their reasoning across a variety of tasks. CriticBench encompasses five reasoning domains: mathematical, commonsense, symbolic, coding, and algorithmic. It compiles 15 datasets and incorporates responses from three LLM families. Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in generation, critique, and correction reasoning, i.e., GQC reasoning. Our findings reveal: (1) a linear relationship in GQC capabilities, with critique-focused training markedly enhancing performance; (2) a task-dependent variation in correction effectiveness, with logic-oriented tasks being more amenable to correction; (3) GQC knowledge inconsistencies that decrease as model size increases; and (4) an intriguing inter-model critiquing dynamic, where stronger models are better at critiquing weaker ones, while weaker models can surprisingly surpass stronger ones in their self-critique. We hope these insights into the nuanced critique-correct reasoning of LLMs will foster further research in LLM critique and self-improvement.

翻译：大语言模型（LLMs）进行批判性反思并优化其推理过程的能力，对其在评估、反馈提供及自我改进等场景中的应用至关重要。本文提出了CriticBench，这是一个旨在全面评估LLMs在不同任务中批判与修正自身推理能力的基准。CriticBench涵盖五个推理领域：数学推理、常识推理、符号推理、代码推理与算法推理。它整合了15个数据集，并纳入了来自三大LLM家族的生成响应。基于CriticBench，我们对17个LLM在生成、批判与修正推理（即GQC推理）中的表现进行了系统评估与分析。研究发现：（1）GQC能力呈现线性关联，专注于批判的训练能显著提升模型表现；（2）修正效果因任务类型而异，逻辑导向的任务更易于被修正；（3）GQC知识存在不一致性，且随模型规模增大而减弱；（4）模型间存在有趣的相互批判动态：较强模型更擅长批判较弱模型，而较弱模型在自我批判方面却能意外地超越较强模型。我们希望这些关于LLMs细致入微的批判-修正推理机制的发现，能够进一步推动LLM批判与自我改进领域的研究。