用图语言模型提升知识图谱检索生成的泛化能力
GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
- 用图语言模型构建检索器，融合图结构与语义信息
- 在多跳问答任务中表现优于现有方法，跨域泛化能力强
- 适合需要跨领域推理的复杂问答系统开发者
基于知识图谱的检索增强生成（RAG）需要能同时捕捉图结构与语义信息的检索器。近期方法尝试使用图神经网络（GNN）建模多跳推理中的图拓扑结构。与此同时，图语言模型（GLMs）作为一种新兴范式，结合了图推理与语言模型的语义能力。本文提出一种基于GLM的检索器，对比分析了GLM、GNN及传统向量搜索三种检索器在单跳与多跳RAG设置下的性能，尤其关注其在未见领域的迁移能力。结果表明，微调后的GLM检索器在跨域场景下表现更优，在两个多跳基准测试中达到当前最优（SOTA）。在本域多跳问答数据集上，其性能与先前工作相当，并随参数规模和子图覆盖率增加展现出良好扩展性。GNN检索器在训练效率高且覆盖范围广，而向量搜索基线在单跳任务中表现最佳。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models. In this work, we introduce a GLM-based retriever and investigate the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and with a particular focus on transferability to unseen domains. Our findings suggest that finetuned GLM retrievers generalize better out of domain, achieving SOTA on two multi-hop benchmarks. On in-domain multi-hop QA datasets they remain comparable to prior work, with promising scaling as parameters and subgraph coverage increase. GNN-based retrievers achieve higher graph coverage with an efficient training setup, whereas the vector-search baseline excels at single-hop datasets.
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。