Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming.

Jiaxu Liu 0001 Xiangyu Yin 0001 Sihao Wu Jianhong Wang Meng Fang Xinping Yi Xiaowei Huang 0001 Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming. 2024 abs/2405.12604 CoRR https://doi.org/10.48550/arXiv.2405.12604 db/journals/corr/corr2405.html#abs-2405-12604