Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks 文章

ArXiv CS.CL2026-05-27NEWSen作者: Lin Mu, Guowei Chu, Li Ni, Lei Sang, Yiwen Zhang
AI 安全
查看原文 →
关系图谱

Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks · 相关技术

相关技术

Large language modelLLMORMODEPLAlanguage modelrsaadversarial modeladversarial examplesVerseSynthetic Aperture RadarReferring expression comprehension (REC)PromptParts-of-Speech (POS) tagsNPUMITLMMHISGranular Alignment ParadigmForEffort Metric Attentionchain-of-thoughtARGANN