从因果视角解析并修复思维链，让大模型推理更可信可懂。
Unveiling and Causalizing CoT: A Causal Pespective
- 用结构因果模型揭示思维链各步骤的因果关系
- 提出CACE指标识别无因果的错误推理步骤
- 通过角色扮演查询算法修复不合理的推理步骤
尽管思维链（CoT）显著提升了大语言模型的推理能力，其内在机制仍是一个“黑箱”。即使能频繁获得正确答案，现有思维链仍难以使人类理解推理过程。本文首次从因果视角揭示并因果化思维链，确保所有推理步骤既正确又可理解。我们采用结构因果模型（SCM）建模思维链的因果关系，并定义了思维链平均因果效应（CACE）来检验各步骤间的因果关联。对于缺乏因果性的步骤（即错误或难以理解的步骤），设计了一种角色扮演式因果查询算法进行修复，生成完整的因果化思维链。在开源与闭源大模型上的实验表明，该方法有效纠正了普遍存在的因果错误，显著提升了模型的推理能力。
原文摘要 · Abstract (English)
Although Chain-of-Thought (CoT) has achieved remarkable success in enhancing the reasoning ability of large language models (LLMs), the mechanism of CoT remains a ``black box''. Even if the correct answers can frequently be obtained, existing CoTs struggle to make the reasoning understandable to human. In this paper, we unveil and causalize CoT from a causal perspective to ensure both correctness and understandability of all reasoning steps (to the best of our knowledge, the first such). We model causality of CoT via structural causal models (SCM) to unveil the reasoning mechanism of CoT. To measure the causality of CoT, we define the CoT Average Causal Effect (CACE) to test the causal relations between steps. For those steps without causality (wrong or unintelligible steps), we design a role-playing causal query algorithm to causalize these steps, resulting a causalized CoT with all steps correct and understandable. Experimental results on both open-source and closed-source LLMs demonstrate that the causal errors commonly in steps are effectively corrected and the reasoning ability of LLMs is significantly improved.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。