arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.18239cs.LG
收藏

揭示与因果化思维链:一种因果视角

Unveiling and Causalizing CoT: A Causal Pespective

Beijing Institute of Technology(北京理工大学);Renmin University of China(中国人民大学)

Jiarun Fu, Lizhong Ding, Hao Li, Pengqi Li, Qiuning Wei, Xu Chen

AI总结:

本文从因果视角揭示并因果化思维链(CoT)机制,通过结构因果模型和CoT平均因果效应衡量步骤因果性,并用角色扮演因果查询算法修正错误步骤,实验证明能显著提升LLM推理能力。

摘要:

尽管思维链(Chain-of-Thought, CoT)在增强大型语言模型(LLMs)的推理能力方面取得了显著成功,但CoT的机制仍然是一个“黑箱”。即使经常能获得正确答案,现有的CoT也难以使推理过程对人类可理解。在本文中,我们从因果视角揭示并因果化CoT,以确保所有推理步骤的正确性和可理解性(据我们所知,这是首次此类工作)。我们通过结构因果模型(SCM)对CoT的因果关系进行建模,以揭示CoT的推理机制。为了衡量CoT的因果性,我们定义了CoT平均因果效应(CACE)来测试步骤之间的因果关系。对于缺乏因果性的步骤(错误或不可理解的步骤),我们设计了一种角色扮演因果查询算法来因果化这些步骤,从而得到一个所有步骤都正确且可理解的因果化CoT。在开源和闭源LLMs上的实验结果表明,步骤中常见的因果错误被有效纠正,且LLMs的推理能力得到显著提升。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑