动态检索增强生成新方法，提升复杂查询的精准度与效率
DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
- 基于属性社区搜索动态提取相关子图，捕捉高阶图结构
- 在四项指标上比现有方法最高提升40%，索引构建时间减少37%
- 适合需要高效精准知识检索的智能问答与搜索引擎场景
由于强大的理解能力，大语言模型（LLMs）已成为现代网络搜索引擎的核心组件。从技术角度看，这种融合体现了检索增强生成（RAG），通过外部知识库为LLMs提供上下文支撑。当前主流方法是基于图的RAG（G-RAG），但普遍忽视图拓扑结构，多依赖低阶结构或预计算的静态社区，限制了对动态复杂查询的处理能力。为此，我们提出DA-RAG，利用属性社区搜索（ACS）根据查询动态提取相关子图，捕获高阶图结构，实现自互补知识的检索。此外，DA-RAG配备面向块层的图索引，支持多粒度高效检索，显著降低计算与经济成本。在多个数据集上的评估表明，其在四项指标上相较现有RAG方法最高提升40%，索引构建时间与令牌开销分别减少最多37%和41%。
原文摘要 · Abstract (English)
Owing to their unprecedented comprehension capabilities, large language models (LLMs) have become indispensable components of modern web search engines. From a technical perspective, this integration represents retrieval-augmented generation (RAG), which enhances LLMs by grounding them in external knowledge bases. A prevalent technical approach in this context is graph-based RAG (G-RAG). However, current G-RAG methodologies frequently underutilize graph topology, predominantly focusing on low-order structures or pre-computed static communities. This limitation affects their effectiveness in addressing dynamic and complex queries. Thus, we propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically. DA-RAG captures high-order graph structures, allowing for the retrieval of self-complementary knowledge. Furthermore, DA-RAG is equipped with a chunk-layer oriented graph index, which facilitates efficient multi-granularity retrieval while significantly reducing both computational and economic costs. We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons across four metrics while reducing index construction time and token overhead by up to 37% and 41%, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。