Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To
Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversight. Recent work evaluates this capability by measuring whether models follow CoT constraints given in the user prompt, and reports very low controllability across models. We argue that this low controllability may not reflect an…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
