作者位次 #2/6SIGIR 2026Poster· Information Retrieval (Short)
When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse
Yingtao Ren · Ziyi Zhao · Yiwei Fu · Xiao Luo · Yu-Cheng Chang · Chin-teng Lin
摘要
Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate generator outputs. Previous methods rely on output-side signals such as perplexity...