一作ACL 2026Findings· Findings of ACL
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
Hao Yang · Qinghua Zhao · Lei Li · Lingyi Meng · Mengda Yu
摘要
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...