paper
referenced-only
2024
paper:arditi-refusal-in-language-models-is-mediated-b-2024

Refusal in language models is mediated by a single direction

ByAndy Arditi·Oscar Obeso·Aaquib Syed·Daniel Paleka·Nina Panickssery·Wes Gurnee+1 more

Related work— refs + corpus + external arXiv

Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.

Similar preprints — Semantic Scholar

Cited by (8)