Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning 事件

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning arXiv:2605.24286v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass the CoT, making the visible reasoning trace misleading even when it appears plausible. We study CoT faithfulness thr