2 papers
cs.AI2026
Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models
Maverick Morales, Tomáš Dominik, Vermut Gao +4
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. Howeve…
cs.LG2026
First-Order Steering: Translating Weight Adaptation into Activation Steering
Sri Pranav Kunda, Alexander Kurz, Tomas Dominik +1
Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior. Composing steering vectors to apply multiple t…