用知识图谱预训练检索器，提升问答生成的准确性。
GPR: Empowering Generation with Graph-Pretrained Retriever
- 直接在知识图谱上预训练检索器，避免文本模型的领域偏差。
- 通过LLM引导图增强，实现问题与子图的精准对齐。
- 适配多种大模型，显著提升问答生成效果。
图检索增强生成（GRAG）对图专用检索器要求高。现有检索器多基于纯文本预训练的语言模型，因领域错配和结构忽视而效果受限。为此，我们提出GPR，一种直接在知识图谱上预训练的图检索器。GPR通过大语言模型引导的图增强，将自然语言问题与相关子图对齐，并采用结构感知目标学习细粒度检索策略。在两个数据集、三种大模型骨架和五种基线上的实验表明，GPR持续提升检索质量与下游生成表现，验证了其作为GRAG可靠检索方案的有效性。
原文摘要 · Abstract (English)
Graph retrieval-augmented generation (GRAG) places high demands on graph-specific retrievers. However, existing retrievers often rely on language models pretrained on plain text, limiting their effectiveness due to domain misalignment and structure ignorance. To address these challenges, we propose GPR, a graph-based retriever pretrained directly on knowledge graphs. GPR aligns natural language questions with relevant subgraphs through LLM-guided graph augmentation and employs a structure-aware objective to learn fine-grained retrieval strategies. Experiments on two datasets, three LLM backbones, and five baselines show that GPR consistently improves both retrieval quality and downstream generation, demonstrating its effectiveness as a robust retrieval solution for GRAG.
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。