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.

翻译：思维链（CoT）在提升大语言模型（LLM）的推理性能方面占据重要地位。尽管已有研究通过检索增强等方法致力于提高CoT的准确性，但关于CoT为何能取得如此成功的严格解释仍不明确。本文通过提出以下问题，在两种不同设置下分析CoT方法：（1）对于零样本CoT，为何使用“让我们逐步思考”提示模型会显著影响其输出？（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？为回答这些问题，我们从霍普菲尔德视角进行了一种自上而下的可解释性分析，并提出了一种用于控制CoT准确性的“读取-控制”方法。通过在三个不同任务的七个数据集上进行大量实验，我们证明了所提框架能够解读CoT的内部工作机制，提供推理错误定位，并通过控制生成正确的推理路径。