Knowledge Graph Unlearning to Defend Language Model Against Jailbreak Attack

Open Webpage

Peihua Mai, Hao Jiang, Ran Yan, Youjia Yang, Zhe Huang, Yan Pang

Published: 01 Jan 2024, Last Modified: 28 Sept 2024Tiny Papers @ ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0