An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
Browse the full NAACL paper archive.
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
Browse the full NAACL paper archive.