Refusal in Language Models Is Mediated by a Single Direction

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda. Refusal in Language Models Is Mediated by a Single Direction. In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, Cheng Zhang 0005, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. 2024. [doi]

Abstract

Abstract is missing.