Defending Jailbreak Prompts via In-Context Adversarial Game.
Yujun Zhou, Yufei Han, Haomin Zhuang, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
Browse the full EMNLP paper archive.
Yujun Zhou, Yufei Han, Haomin Zhuang, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
Browse the full EMNLP paper archive.