Man Hu 0001, Yahui Ding, Yatao Yang 0001, Liangyu Chen, Yanhao Jia, Shuai Zhao 0007. DUP: Detection-guided Unlearning for Backdoor Purification in Language Models. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 31059-31067, AAAI Press, 2026. [doi]
Abstract is missing.