arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.10150cs.CLcs.AI

基于层级知识的检索增强生成

Retrieval-Augmented Generation with Hierarchical Knowledge

  • CSE, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学)

机构由 AI 辅助整理,请以论文原文为准。

Haoyu Huang, Yongfeng Huang, Junjie Yang, Zhenyu Pan, Yongqiang Chen, Kaili Ma, Hongzhi Chen, James Cheng

更新

AI总结:

本文提出HiRAG,一种利用层级知识增强检索增强生成系统在索引与检索中语义理解和结构捕获能力的新方法,实验证明其性能显著优于现有最先进基线。

AI中文摘要:

基于图的检索增强生成(RAG)方法显著提升了大型语言模型(LLMs)在领域特定任务中的性能。然而,现有的RAG方法未能充分利用人类认知中自然固有的层级知识,这限制了RAG系统的能力。在本文中,我们提出了一种新的RAG方法,称为HiRAG,它利用层级知识来增强RAG系统在索引和检索过程中的语义理解与结构捕获能力。我们的广泛实验表明,HiRAG在性能上相较于最先进的基线方法取得了显著的提升。

英文摘要:

Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks. However, existing RAG methods do not adequately utilize the naturally inherent hierarchical knowledge in human cognition, which limits the capabilities of RAG systems. In this paper, we introduce a new RAG approach, called HiRAG, which utilizes hierarchical knowledge to enhance the semantic understanding and structure capturing capabilities of RAG systems in the indexing and retrieval processes. Our extensive experiments demonstrate that HiRAG achieves significant performance improvements over the state-of-the-art baseline methods.

补充信息

↑