Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li, Tong Yu, Xiang Chen, Ritwik Sinha, Jingbo Shang
Abstract
Recent advances in chain-of-thought (CoT) prompting have demonstrated the ability of large language models (LLMs) to perform multi-step reasoning. While prior work focuses on improving CoT generation quality or attributing token-level importance, we propose a novel framework to structurally analyze the latent dynamics of CoT trajectories for interpretability. Our method segments generated CoT into discrete reasoning steps, abstracts each step into a spectral embedding based on the eigenvalues of token-level Gram matrices, and clusters these embeddings into semantically meaningful latent states. We model the global evolution of reasoning as a first-order Markov chain over latent clusters, yielding interpretable transition structures. Through t-SNE visualizations and Monte Carlo rollouts, we uncover consistent trajectories across tasks and models, supporting the hypothesis that LLM reasoning follows globally coherent yet abstract paths.
BibTeX
@inproceedings{emnlp2025_explainablechain,
title = {Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics},
author = {Sheldon Yu and Yuxin Xiong and Junda Wu and Xintong Li and Tong Yu and Xiang Chen and Ritwik Sinha and Jingbo Shang and Julian McAuley},
booktitle = {EMNLP 2025},
year = {2025}
}