Work

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation

Year: 2026

Type: conference-paper

Abstract: Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood.We analyze CoT's operational principles by reversely tracing information flow across decoding, projection, and activation phases.Our quantitative analysis suggests that CoT may serve as a decoding space pruner, leveraging answer templates to guide output generation, with higher template adherence strongly correlating with improved performance.Furthermore, we surprisingly find that CoT modulates neuron engagement in a task-dependent manner: reducing neuron activation in open-domain tasks, yet increasing it in closed-domain scenarios.These findings offer a novel mechanistic interpretability framework and critical insights for enabling targeted CoT interventions to design more efficient and robust prompts.We released our code and data at https://github.com/How-Young-X/cot.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.255

Authors: Hao Yang, Qinghua Zhao, Lei Li, Lingyi Meng, Mengda Yu

Institutions: Nanjing University, Hefei University, Beijing Institute of Technology, University of Pittsburgh, The Ohio State University Wexner Medical Center

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Nanjing University

Awards: G221534468, G3068689681, G5721869488