Findeis, Arduin

2 publications

ICLR 2025 Inverse Constitutional AI: Compressing Preferences into Principles Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Samuel Albanie, Robert D. Mullins
ICMLW 2023 Do LLMs Selectively Encode the Goal of an Agent's Reach? Laura Ruis, Arduin Findeis, Herbie Bradley, Hossein A. Rahmani, Kyoung Whan Choe, Edward Grefenstette, Tim Rocktäschel