AI RESEARCH
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
arXiv CS.LG
•
ArXi:2604.23351v1 Announce Type: cross Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation patching: transferring token-level hidden states from a CoT generation to a direct-answer run for the same question, then measuring the effect on final-answer accuracy.