How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation 文章

ArXiv CS.CL2026-06-16NEWSen作者: Yimeng Chen, Zhe Ren, Firas Laakom, Yu Li, Dandan Guo, J\"urgen Schmidhuber
查看原文 →
关系图谱

How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation · 相关技术

相关技术

Large language modelLLM