Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context LearningShuai Zhao,Meihuizi Jia,Anh Tuan Luu,Fengjun Pan,Jinming WenEMNLP 2024（2024）引用 40|浏览9关键词Topic Modeling,Sequence-to-Sequence LearningAI 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
