A

Aruna Sankaranarayanan, Amir Zur, Atticus Geiger, Dylan Hadfield-Menell

Aruna Sankaranarayanan, Amir Zur, Atticus Geiger, Dylan Hadfield-Menell의 전문분석자료

Academic · 약 1분

Surgical Activation Steering via Generative Causal Mediation

arXiv:2602.16080v1 Announce Type: new Abstract: Where should we intervene in a language model (LM) to control behaviors that are diffused across many tokens of a …

Aruna Sankaranarayanan, Amir Zur, Atticus Geiger, Dylan Hadfield-Menell
조회수 49회