2 papers
cs.AI2025
The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
Jeremias Ferrao, Matthijs van der Lende, Ilija Lichkovski +1
Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL),…
cs.AI2025
EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
Ilija Lichkovski, Alexander Müller, Mariam Ibrahim +1
Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors,…