Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
North American Chapter of the Association for Computational Linguistics（2025）
关键词
Black Box Models,Defenses,Topic Modeling,Adversarial Examples
AI 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