作者位次 #3/4ACL 2026Poster· Natural Language Processing
Structure Guided Retrieval-Augmented Generation for Factual Queries
Miao Xie · Xiao Zhang · Yi Li · Chunli Lv
摘要
Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect. However, existing RAG approaches predominantly rely on vector similarity for retrieval, which is prone to semantic noise and fails...