Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic

作者：Xin Zheng, Jie Lou, Boxi Cao, Xueru Wen, Yuqiu Ji, Hongyu Lin, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun · 年份：2025 · DOI：10.18653/v1/2025.findings-acl.89 · 被引用次数：3 · 研究领域：Topic Modeling

Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs.However, current approaches mainly involve basic prompts for intuitive instance-level feedback, which resembles System-1 processes and limits the reasoning capabilities.Moreover, there is a lack of in-depth investigations into the relationship between LLM's ability to criticize and its task-solving performance.To address these issues, we propose Critic-CoT, a novel framework that pushes LLMs toward System-2-like critic capability.Through a step-wise CoT reasoning paradigm and the automatic construction of weak-supervision data without human annotation, Critic-CoT enables LLMs to engage in slow, analytic self-critique and refinement, thereby improving their reasoning abilities.Experiments on GSM8K and MATH and out-of-domain evaluation demonstrate that our enhanced model significantly boosts tasksolving performance by filtering out invalid solutions or iterative refinement.Furthermore, we investigate the intrinsic correlation between critique and task-solving abilities within LLMs, discovering that these abilities can mutually reinforce each other rather than conflict.