JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification.
Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Zhaoye Li, Bin Ji, Baosheng Wang, Jie Yu
Browse the full ACL paper archive.
Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Zhaoye Li, Bin Ji, Baosheng Wang, Jie Yu
Browse the full ACL paper archive.