Reasoning-Token Spikes Under Prompted Untruthful Responses 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 t...
Maverick Morales, T. Dominik, Vermut Gao et al.
· 0 citations