3 papers
cs.LG2026
Predicting Future Behaviors in Reasoning Models Enables Better Steering
Evgenii Kortukov, Piotr Komorowski, Florian Klein +5
Deployed large reasoning models (LRMs) often behave unexpectedly. Test-time steering controls LRM outputs by intervening on their hidden representations, but it can degrade output…
cs.LG2026
ASIDE: Architectural Separation of Instructions and Data in Language Models
Egor Zverev, Evgenii Kortukov, Alexander Panfilov +5
Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks. In particular, previous work has…
cs.LG2025
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
Alexander Panfilov, Evgenii Kortukov, Kristina NikoliÄ +6
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrifici…