用知识图谱增强查询语义，提升检索精度
KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
- 通过构建子图并补全关系，丰富复杂查询的上下文表示
- 在RAGBench和MultiHop-RAG上提升mAP 4-6%，Recall@25提升2-3%
- 无需微调，可适配不同大小的LLM，适合多跳问答等挑战任务
将知识图谱（KG）与大语言模型（LLM）结合，有望显著提升检索增强生成（RAG）系统中检索阶段的性能。本文提出一种名为KG-CQR的新框架，用于上下文查询检索（CQR），通过以语料为中心的知识图谱，增强复杂输入查询的上下文表征。不同于以往主要解决语料级上下文丢失的方法，KG-CQR聚焦于查询层面的丰富化，利用结构化关系表示提取并补全相关知识图谱子图，生成语义丰富的查询上下文。该框架包含子图提取、补全和上下文生成三个模块，作为与模型无关的流水线，可在不额外训练的前提下适配不同规模的LLM。在RAGBench和MultiHop-RAG数据集上的实验表明，相比强基线模型，KG-CQR在mAP上提升4-6%，Recall@25提升2-3%。此外，在多跳问答等高难度RAG任务中，引入KG-CQR后，检索有效性持续优于现有基线。
原文摘要 · Abstract (English)
The integration of knowledge graphs (KGs) with large language models (LLMs) offers significant potential to improve the retrieval phase of retrieval-augmented generation (RAG) systems. In this study, we propose KG-CQR, a novel framework for Contextual Query Retrieval (CQR) that enhances the retrieval phase by enriching the contextual representation of complex input queries using a corpus-centric KG. Unlike existing methods that primarily address corpus-level context loss, KG-CQR focuses on query enrichment through structured relation representations, extracting and completing relevant KG subgraphs to generate semantically rich query contexts. Comprising subgraph extraction, completion, and contextual generation modules, KG-CQR operates as a model-agnostic pipeline, ensuring scalability across LLMs of varying sizes without additional training. Experimental results on RAGBench and MultiHop-RAG datasets demonstrate KG-CQR's superior performance, achieving a 4-6% improvement in mAP and a 2-3% improvement in Recall@25 over strong baseline models. Furthermore, evaluations on challenging RAG tasks such as multi-hop question answering show that, by incorporating KG-CQR, the performance consistently outperforms the existing baseline in terms of retrieval effectiveness
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。