Refusal in Language Models Is Mediated by a Single Direction
Year: 2024
Type: conference-paper
DOI: 10.52202/079017-4322
Authors: Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda
Subfield: Language and Linguistics
Field: Arts and Humanities
Domain: Social Sciences
Open Access status: closed
OpenAlex ID: W4415800641