arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.12255cs.CLcs.AIcs.HCcs.LG
收藏

基于Hopfield视角的思维链推理解释

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

KAUST(阿卜杜拉国王科技大学);Soochow University(苏州大学);University of Southampton(南安普顿大学);Tongji University(同济大学);Universität Hamburg(汉堡大学);Huazhong University of Science and Technology(华中科技大学)

Lijie Hu, Liang Liu, Shu Yang, Xin Chen, Hongru Xiao, Mengdi Li, Pan Zhou, Muhammad Asif Ali, Di Wang

AI总结:

本研究针对大语言模型中思维链(CoT)的生效机制尚不明确的问题,从Hopfield视角开展可解释分析,提出Read-and-Control方法,经多数据集多任务实验验证可解读CoT机制、定位错误并控制生成正确推理路径。

摘要:

思维链(Chain-of-Thought, CoT)在提升大语言模型(large language models, LLMs)的推理性能方面占据重要地位。虽然部分研究聚焦于通过检索增强等方法提升CoT的准确率,但关于CoT为何能取得如此成效的严谨解释仍不明确。本文在两种不同设置下分析CoT方法,并提出以下问题:(1)对于零样本CoT,为何用“让我们一步步思考”提示模型会对其输出产生显著影响?(2)对于少样本CoT,为何在向模型提问前提供示例能大幅提升其推理能力?为解答这些问题,我们从Hopfield视角开展自上而下的可解释性分析,并提出一种用于控制CoT准确率的Read-and-Control方法。通过在七个数据集上针对三类不同任务开展大量实验,我们证明该框架能够解读CoT的内部运作机制,实现推理错误定位,并控制模型生成正确的推理路径。

英文摘要:

Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, yet a rigorous explanation for why CoT achieves such success remains unclear. In this paper, we analyze CoT methods under two different settings by asking the following questions: (1) For zero-shot CoT, why does prompting the model with "let's think step by step" significantly impact its outputs? (2) For few-shot CoT, why does providing examples before questioning the model could substantially improve its reasoning ability? To answer these questions, we conduct a top-down explainable analysis from the Hopfieldian view and propose a Read-and-Control approach for controlling the accuracy of CoT. Through extensive experiments on seven datasets for three different tasks, we demonstrate that our framework can decipher the inner workings of CoT, provide reasoning error localization, and control to come up with the correct reasoning path.

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。

↑