Reasoning Models Don't Always Say What They Think

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model’s CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully representing models’ actual reasoning processes. We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in the prompts and find: (1) for most settings and models tested, CoTs reveal their usage of hints in at least 1% of examples where they use the hint, but the reveal rate is often below 20%, (2) outcome-based reinforcement learning initially improves faithfulness but plateaus without saturating, and (3) when reinforcement learning increases how frequently hints are used (reward hacking), the propensity to verbalize them does not increase, even without training against a CoT monitor. These results suggest that CoT monitoring is a promising way of noticing undesired behaviors during training and evaluations, but that it is not sufficient to rule them out. They also suggest that in settings like ours where CoT reasoning is not necessary, test-time monitoring of CoTs is unlikely to reliably catch rare and catastrophic unexpected behaviors.

arxiv.org/abs/2505.05410v1

About
Latest Posts

Ryan Watkins

Professor at George Washington University

I am a Professor with Human-Technology Collaboration and Educational Technology programs at George Washington University in Washington DC. I have written 12 books and more than 100 articles, and I co-host of the Parsing Science podcast where scientists tell the stories behind their research. I am also the developer of the WeShareScience.com online platform for sharing research videos, and SciencePods.com where researchers can create free podcasts about their science. My research interests include human interactions with intelligent machines, needs, needs assessments, and instructional design.