arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.09957cs.CL
收藏

FRAG:一种基于知识图谱的检索增强生成的灵活模块化框架

FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs

University of Science and Technology of China(中国科学技术大学);MIRACLE Center(MIRACLE中心)

Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, Xike Xie, S Kevin Zhou

AI总结:

FRAG提出灵活模块化KG-RAG框架,仅基于查询估计推理路径跳数并分类,采用适应性检索策略,兼顾检索质量与灵活性,无需额外微调,实现高效低耗的最优性能。

摘要:

为了缓解大型语言模型(LLMs)中的幻觉和知识缺乏问题,基于知识图谱(KG)的检索增强生成(RAG)通过利用知识图谱作为外部资源来增强LLMs的推理能力,显示出良好的潜力。然而,现有的KG-RAG方法在灵活性和检索质量之间难以权衡。模块化方法通过避免在检索过程中使用KG微调模型来优先考虑灵活性,导致检索策略固定且检索质量次优。相反,耦合方法将KG信息嵌入模型中以提高检索质量,但牺牲了灵活性。在本文中,我们提出了一种新颖的灵活模块化KG-RAG框架,称为FRAG,它协同了两种方法的优势。FRAG仅基于查询估计推理路径的跳数范围,并将其分类为简单或复杂。为了匹配查询的复杂性,应用定制的流水线以确保高效且准确的推理路径检索,从而促进最终的推理过程。通过使用查询文本而非知识图谱来推断推理路径的结构信息,并采用适应性检索策略,FRAG在保持灵活性的同时提高了检索质量。此外,FRAG不需要额外的LLMs微调或调用,显著提高了效率并节约了资源。大量实验表明,FRAG以高效率和低资源消耗实现了最先进的性能。

英文摘要:

To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as external resource to enhance LLMs reasoning. However, existing KG-RAG approaches struggle with a trade-off between flexibility and retrieval quality. Modular methods prioritize flexibility by avoiding the use of KG-fine-tuned models during retrieval, leading to fixed retrieval strategies and suboptimal retrieval quality. Conversely, coupled methods embed KG information within models to improve retrieval quality, but at the expense of flexibility. In this paper, we propose a novel flexible modular KG-RAG framework, termed FRAG, which synergizes the advantages of both approaches. FRAG estimates the hop range of reasoning paths based solely on the query and classify it as either simple or complex. To match the complexity of the query, tailored pipelines are applied to ensure efficient and accurate reasoning path retrieval, thus fostering the final reasoning process. By using the query text instead of the KG to infer the structural information of reasoning paths and employing adaptable retrieval strategies, FRAG improves retrieval quality while maintaining flexibility. Moreover, FRAG does not require extra LLMs fine-tuning or calls, significantly boosting efficiency and conserving resources. Extensive experiments show that FRAG achieves state-of-the-art performance with high efficiency and low resource consumption.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑