Diversity Helps Jailbreak Large Language Models

Published in , 2025

Weiliang Zhao, Daniel Ben-Levi, Wei Hao,Junfeng Yang, Chengzhi Mao. "Diversity Helps Jailbreak Large Language Models", Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025. https://arxiv.org/abs/2411.04223