arXiv cs.AI· Zicheng Zhao, Linhao Luo, Zongji Yu, Junnan Dong, Yanchao Tan, Shirui Pan, Chen Gong·· 2 小时前AI 评分28
UniGFM-RAG：统一图基础模型与大语言模型实现端到端检索与推理
UniGFM-RAG: Unify Graph Foundation Models and Large Language Models for End-to-End Retrieval and Reasoning
AI 导读
研究者提出 UniGFM-RAG，一个将 GFM 检索器与 LLM 生成器紧耦合的端到端 GraphRAG 框架，通过可微分图桥接把节点嵌入投影为软加权图前缀注入 LLM 生成，并借助基于查询-文档语义相似度伪标签的语义引导蒸馏降低对人工标注的依赖。在三个多跳问答数据集和三个域外 GraphRAG 基准上，该方法持续超越强基线并具备良好泛化性。
正文 · 原文
Abstract:Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge. Graph Retrieval-Augmented Generation (GraphRAG) addresses this challenge by organizing fragment knowledge as graphs, while recent Graph Foundation Models (GFMs) further improve GraphRAG with graph-native retrieval and reasoning capabilities. However, existing GraphRAG methods usually adopt decoupled retrieve-then-generate pipelines, which create objective misalignment between retrieval and reasoning, and training GFM retrievers typically depends on expensive human annotations. To address these limitations, we propose \ourmethod, a unified end-to-end GraphRAG framework that tightly couples a GFM retriever with an LLM generator. Given a query, the GFM retriever first reasons over the graph to score and retrieve relevant document nodes. These node embeddings are then passed through a fully differentiable graph bridge, which projects them into soft-weighted graph prefixes according to retrieval scores and combines them with raw document texts to form graph-augmented prompts. In this way, structural information is injected directly into LLM generation, while the final answer loss can be back-propagated through the bridge to jointly optimize retrieval and reasoning. To stabilize training and reduce reliance on costly annotations, we further introduce a semantic-guided distillation module that provides auxiliary supervision using pseudo-labels derived from query-document semantic similarities. Extensive experiments on three multi-hop QA datasets and three out-of-domain GraphRAG benchmarks show that \ourmethod consistently outperforms strong baseline methods and generalizes well, which demonstrates the effectiveness of end-to-end GraphRAG with tightly integrated GFM retrieval and LLM reasoning.
| Comments: | 16 pages, 8 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34866 [cs.AI] |
| (or arXiv:2610.34866v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34866 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zicheng Zhao [view email]
[v1]
Mon, 26 Oct 2026 05:30:07 UTC (4,491 KB)
来源：arXiv cs.AI · arxiv.org