2 papers
cs.LG2024
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
Phillip Guo, Aaquib Syed, Abhay Sheshadri +2
Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling pe…
cs.LG2024
Refusal in Language Models Is Mediated by a Single Direction
Andy Arditi, Oscar Obeso, Aaquib Syed +4
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this ref…