Lune

EMNLP Findings2025

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, Julian J. McAuley

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps cites Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
  • Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps cites Large Language Models are Zero-Shot Reasoners
  • Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting cites Large Language Models are Zero-Shot Reasoners
  • Automatic Chain of Thought Prompting in Large Language Models cites Large Language Models are Zero-Shot Reasoners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Measuring Chain of Thought Faithfulness by Unlearning Reasoning StepsMartin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, Yonatan BelinkovEMNLP 2025 · 37 citations
  2. Unveiling the Entropy Dynamics of Chain-of-Thought ReasoningTING XU, Xu He, Yupu Lu, Jiankai Sun et al.ICML 2026 · 2 citations
  3. Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment RewardShizhan Gong, Minda Hu, Qiyuan Zhang, Chen Ma et al.CVPR 2026 · 1 citation
  4. WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient ReasoningGagan Mundada, Zihan Huang, Rohan Surana, Sheldon Yu et al.ICML 2026
  5. SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language ModelsMing Chen, Wenyao Li, Chao Liang, Shi Gu et al.ACL 2026

Builds on13

  1. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  2. Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought PromptingMiles Turpin, Julian Michael, Ethan Perez, Samuel R. BowmanNeurIPS 2023 · 1,792 citations
  3. Automatic Chain of Thought Prompting in Large Language ModelsZhuosheng Zhang, Aston Zhang, Mu Li, Alex SmolaICLR 2023 · 234 citations
  4. Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion AttackNingfei Wang, Yunpeng Luo, Takami Sato, Kaidi Xu et al.ICCV 2023 · 65 citations
  5. Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention MapsYung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna et al.EMNLP 2024 · 18 citations

Related papers

  1. Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMsZhen Xiong, Yujun Cai, Zhecheng Li, Yiwei WangEMNLP 2025
  2. Learning to Reason over Continuous Tokens with Reinforcement LearningYiran Zhao, Yuhui Xu, Doyen Sahoo, Caiming Xiong et al.ICLR 2026 · 1 citation
  3. Streaming Hallucination Detection in Long Chain-of-Thought ReasoningHaolang Lu, Minghui Pan, Ripeng Li, Guoshun Nan et al.ACL Findings 2026
  4. SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language ModelsYunlong Chu, Minglai Shao, Yuhang Liu, Bing Hao et al.KDD 2026 · 2 citations
  5. Exploring Layer Activation Dynamic of CoT via Knowledge ProbeChuanxin Zhang, Jiajun Liu, Yao He, Wenjun Ke et al.ACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines