作者位次 #6/9ACL 2026Poster· Natural Language Processing
L ogic P oison: Logical Attacks on Graph Retrieval-Augmented Generation
Yilin Xiao · Jin Chen · Qinggang Zhang · Yujing Zhang · Chuang Zhou · Longhao Yang · Lingfei Ren · Xin Yang · Xiao Huang
摘要
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems demonstrate inherent resistance...