AI RESEARCH
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
arXiv CS.AI
•
ArXi:2507.20758v2 Announce Type: replace 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.