Backdoor defense for large language models with weak-to-strong knowledge distillation

Open Webpage

Yuwen Li, Xinyi Wu, Zhongliang Guo, Luwei Xiao, Yanhao Jia, Shuai Zhao

Published: 2026, Last Modified: 02 Mar 2026Pattern Recognit. 2026EveryoneRevisionsBibTeXCC BY-SA 4.0