可解释的链式思维推理：对状态感知推理动态的实证分析
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
AI总结：
本文提出了一种状态感知的转换框架，通过结构化潜在动态分析链式思维推理的语义演变和转换，提升推理过程的可解释性。
摘要：
最近的链式思维（CoT）提示方法使大型语言模型（LLMs）能够进行多步推理。然而，此类推理的可解释性仍然有限，先前的研究主要集中在局部token级归因上，使得推理步骤的高层语义角色及其转换仍处于未探索的状态。在本文中，我们引入了一种状态感知的转换框架，将CoT轨迹抽象为结构化的潜在动态。具体来说，为了捕捉CoT推理的演变语义，每个推理步骤通过token级嵌入的频谱分析进行表示，并聚类为语义连贯的潜在状态。为了表征推理的全局结构，我们将其进展建模为马尔可夫链，从而得到推理过程的结构化和可解释的视图。这种抽象支持一系列分析，包括语义角色识别、时间模式可视化和一致性评估。
英文摘要：
Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.
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。
