Reasoning Models Don’t Always Say What They Think

Chen et al., 2025, Reasoning Models Don’t Always Say What They Think (arXiv preprint arXiv:2505.05410)

Subscriber deck — free during early access

1 cards in “7.1 Implications for Test-time CoT Monitoring Safety Cases” · whole deck

7.1 Implications for Test-time CoT Monitoring Safety Cases

What do Chen et al. conclude about relying on chain-of-thought monitoring?
It is useful for noticing unwanted behavior that is frequent or needs many steps, since some instance will likely be verbalized, but not reliable enough to rule out behaviors a model can perform without reasoning out loud, such as rare one-step actions.
- Chen et al., 2025, Reasoning Models Don’t Always Say What They Think (arXiv preprint arXiv:2505.05410), §7.1

Source

Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vlad Mikulik, Samuel R. Bowman, Jan Leike, Jared Kaplan and Ethan Perez. 2025. Reasoning Models Don’t Always Say What They Think. In arXiv preprint arXiv:2505.05410. https://arxiv.org/abs/2505.05410