What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation 事件

What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation arXiv:2605.26795v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a probe-time question: given a fixed rationale in context, what in that text changes the answer? We identify two complem