让弱检索器与大模型对齐，提升图结构知识增强生成效果
Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
- 用大模型反馈优化弱监督训练的检索器，去除错误信号
- 重构检索结果为逻辑连贯的证据链，性能提升最高达10%
- 适合需要降低幻觉、提升推理效率的研究者和应用
基于图的检索增强生成（GraphRAG）使大语言模型（LLMs）能够利用最新知识图谱（KGs）中的结构化外部知识，减少幻觉。然而，当前方法常依赖弱检索器：一、缺乏真实标签，检索器通常在弱监督下训练，易引入虚假信号；二、图数据抽象导致检索结果杂乱无章。为此，我们提出精炼图RAG（ReG），通过大模型反馈消除虚假信号并提升监督质量，同时引入结构感知重组织模块，将检索结果重构为逻辑连贯的证据链。在主流基准测试中，ReG在不同LLM主干上显著且一致提升性能，最高达10%。更优的监督质量使ReG仅用5%训练数据即可达到顶尖水平，并可迁移至分布外的知识图谱。当应用于推理型大模型时，ReG将推理令牌消耗降低最多30%，性能提升最高4%。
原文摘要 · Abstract (English)
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to ground responses with structured external knowledge from up-to-date knowledge graphs (KGs) and reduce hallucinations. However, LLMs often rely on a weak retriever in graph-based RAG: I) Due to the lack of ground truth, the retriever is often trained on weak supervision, which often introduces spurious signals to the LLMs. II) Due to the abstraction of graph data, the retrieved knowledge is often presented in unorganized forms. To mitigate the issue, we present Refined Graph-based RAG (ReG) to align weak retrievers to LLMs for graph-based RAG. Specifically, ReG incorporates LLM feedback to get rid of spurious signals and improve the quality of the supervision. Meanwhile, ReG introduces a structure-aware reorganization module to refactor the retrieval results into logically coherent evidence chains. Experiments on prominent benchmarks demonstrate that ReG significantly and consistently brings improvements across different LLM backbones by up to 10%. The improved supervision quality enables ReG to match the state-of-the-art performance with 5% training data and to transfer to out-of-distribution KGs. Notably, when adopted to reasoning-based LLMs, ReG reduces the reasoning token cost by up to 30% and improves the performance by up to 4%.
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。