arXiv cs.CLPaper
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
This is a credibility hit on interpretability through CoT. You can't trust that step-level LLM judges or process reward models are actually identifying the steps that matter. If you're using CoT for debugging or step-level supervision, you're getting a narrative, not a causal readout. The work identifies a real gap between appearance and function.