Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Open Webpage

Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, Danqi Chen

Published: 01 Jan 2024, Last Modified: 27 Sept 2024ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0