Moderate-fitting As a Natural Backdoor Defender for Pre-trained Language Models.Biru Zhu,Yujia Qin,Ganqu Cui,Yangyi Chen,Weilin Zhao,Chong Fu,Yangdong Deng,Zhiyuan Liu,Jingang Wang,Wei Wu,Maosong Sun,Ming GuNEURIPS 2022（2022）引用 35|浏览222关键词Backdoor Defense,Pre-trained Language ModelsAI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
