Reasoning Correctives: Faithfulness / Overthinking / Contamination

Editorial record

Plain-language summary

By inserting biasing features into prompts, such as always marking option (A) as correct, the authors showed models would follow the bias while writing plausible reasoning that never mentioned it, demonstrating that CoT explanations can be post-hoc rather than causal. Related findings cover overthinking, where longer reasoning hurts accuracy, and contamination, where memorized answers masquerade as derived ones. The collective correction is that a readable chain-of-thought is not automatically a faithful account of the computation, so it cannot be trusted as an interpretability or safety signal without further verification.