Refusal in language models is mediated by a single direction in residual stream activations that can be erased to disable safety or added to elicit refusal.
arXiv:2311.09827
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
StrongREJECT provides a standardized benchmark and evaluator for jailbreak attacks that aligns better with human judgments than prior methods and reveals that successful jailbreaks often reduce model capabilities.
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.
citing papers explorer
-
Refusal in Language Models Is Mediated by a Single Direction
Refusal in language models is mediated by a single direction in residual stream activations that can be erased to disable safety or added to elicit refusal.
-
A StrongREJECT for Empty Jailbreaks
StrongREJECT provides a standardized benchmark and evaluator for jailbreak attacks that aligns better with human judgments than prior methods and reveals that successful jailbreaks often reduce model capabilities.
-
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.