Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models
Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic chain-of-thought monitoring depends on reasoning traces being legible and sufficiently faithful to the underlying computations that produced the model's behavior, not to mention accessible. Moreover, there…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
