作者位次 #2/7ACL 2026Findings· Findings of ACL
RIPRAG : Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning
Meng Xi · Sihan Lv · Yechen Jin · Guanjie Cheng · Naibo Wang · Ying Li · Jianwei Yin
摘要
Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become a core technology for tasks such as question-answering (QA) and content generation. RAG poisoning is an attack method to induce LLMs to generate the attacker’s expected text by injecting poisoned docume...