Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Open Webpage

Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson

Published: 2024, Last Modified: 07 Jan 2026ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0