用伪知识图谱提升大模型检索准确率，解决信息碎片化问题。
Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM
- 构建伪知识图谱，融合元路径与图内文本实现多策略检索
- 在Open Compass和MultiHop-RAG上显著提升复杂关系推理能力
- 适合需要精准、连贯长文本生成的智能问答系统使用
大型语言模型（LLMs）已彻底改变自然语言处理。然而，这些模型在从海量数据中检索精确信息时仍面临挑战。检索增强生成（RAG）通过结合外部检索系统提升了响应的准确性与上下文相关性。尽管如此，现有RAG在高容量、低信息密度数据库中仍难以实现全面检索，且缺乏关系感知能力，导致答案碎片化。为此，本文提出伪知识图谱（PKG）框架，通过整合元路径检索、图内文本与向量检索，克服上述局限。该框架保留原始自然语言文本，并融合多种检索技术，提供更丰富的知识表示，显著提升信息检索精度。在Open Compass和MultiHop-RAG基准上的广泛评估表明，该框架在处理大规模数据与复杂关系方面具有卓越性能。
原文摘要 · Abstract (English)
The advent of Large Language Models (LLMs) has revolutionized natural language processing. However, these models face challenges in retrieving precise information from vast datasets. Retrieval-Augmented Generation (RAG) was developed to combining LLMs with external information retrieval systems to enhance the accuracy and context of responses. Despite improvements, RAG still struggles with comprehensive retrieval in high-volume, low-information-density databases and lacks relational awareness, leading to fragmented answers. To address this, this paper introduces the Pseudo-Knowledge Graph (PKG) framework, designed to overcome these limitations by integrating Meta-path Retrieval, In-graph Text and Vector Retrieval into LLMs. By preserving natural language text and leveraging various retrieval techniques, the PKG offers a richer knowledge representation and improves accuracy in information retrieval. Extensive evaluations using Open Compass and MultiHop-RAG benchmarks demonstrate the framework's effectiveness in managing large volumes of data and complex relationships.
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。