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 2407.21276cs.AIcs.CL
收藏

面向多级检索增强生成的知识金字塔构建

Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation

The Hong Kong Polytechnic University(香港理工大学)

Rubing Chen, Xulu Zhang, Jiaxin Wu, Wenqi Fan, Xiao-Yong Wei, Qing Li

AI总结:

针对现有RAG方法重召回、精度不足的问题,本文提出包含三层结构的PolyRAG知识金字塔方法,采用跨层增强、过滤和瀑布式检索策略,在两个领域基准上优于19种SOTA方法,可将GPT-4的F1值提升395%。

摘要:

本文针对现有知识增强问答框架(尤其是主要聚焦于提升召回率的检索增强生成(Retrieval-Augmented Generation,RAG)方法)的精度提升需求展开研究。我们在RAG框架内提出了一种多层知识金字塔方法,以在精度和召回率之间实现更好的平衡。知识金字塔由三层构成:本体(Ontologies)、知识图谱(Knowledge Graphs,KGs)以及基于文本块的原始文本。我们采用跨层增强技术来实现全面的知识覆盖,以及本体模式和实例的动态更新。为保证结构紧凑,我们利用跨层过滤方法对知识图谱中的知识进行浓缩。我们提出的方法名为PolyRAG,采用瀑布式检索模型,从金字塔顶层开始向下检索,直至获得置信度足够的答案。我们引入了两个面向领域特定知识检索的基准,一个属于学术领域,另一个属于金融领域。通过全面实验验证了该方法的有效性,其性能优于19种SOTA(当前最优)方法。一项令人鼓舞的发现是,所提方法对GPT-4实现了增强,将其F1值从0.1636提升至0.8109,增幅达395%。

英文摘要:

This paper addresses the need for improved precision in existing knowledge-enhanced question-answering frameworks, specifically Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances. To ensure compactness, we utilize cross-layer filtering methods for knowledge condensation in KGs. Our approach, named PolyRAG, follows a waterfall model for retrieval, starting from the top of the pyramid and progressing down until a confident answer is obtained. We introduce two benchmarks for domain-specific knowledge retrieval, one in the academic domain and the other in the financial domain. The effectiveness of the methods has been validated through comprehensive experiments by outperforming 19 SOTA methods. An encouraging observation is that the proposed method has augmented the GPT-4, providing 395% F1 gain by improving its performance from 0.1636 to 0.8109.

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。

↑