Skip to content
Preprint

UniGFM-RAG: Unify Graph Foundation Models and Large Language Models for End-to-End Retrieval and Reasoning

Oct 2026 · 0 citations · 66 references
Computer Science

TL;DR

This work proposes \ourmethod, a unified end-to-end GraphRAG framework that tightly couples a GFM retriever with an LLM generator and introduces a semantic-guided distillation module that provides auxiliary supervision using pseudo-labels derived from query-document semantic similarities.

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.

View source

Similar papers

#machine learning Preprint Oct 2026

Towards a Learnable Retriever for Textual Graph Question Answering

Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured knowledge. Despite extensive efforts, existing methods still face two key gaps. The first is an architectural gap: existing...

Kai-Feng Jin, Yu-Chen Yan, Zhichen Zeng et al. · 0 citations
Conference Open access Sep 2026

A Prompt-Based Graph Reasoning Method for Inductive Knowledge Graphs Based on Unified Semantic Encoding

Inductive knowledge graph (KG) reasoning aims to predict missing facts on graphs with unseen entities by learning transferable relational patterns. Existing methods suffer from insufficient relation discriminability, weak cross-graph transfer, and suboptimal use of query-relevant context. Inspired by the in-context lea...

Yu-Hao Wang, Jin-Hui Zhang, Yuxuan Zhao et al. · 0 citations
Open access Sep 2026

PoP-RAG: Holistic Query Planning for GraphRAG

PoP-RAG is proposed, which features a passage-on-edge (PoE) graph that links the passages with graph edges to resolve the one-to-many entity-passage mapping problem and enables targeted retrieval for each sub-query and ensures transparent response derivation logic, thus enhancing explainability.

Xin-Tong Hu, Qi-Ming Zeng, Yu-Hao Lin et al. · 1 citation
Open access Oct 2026

High-Information-Density Knowledge Graph Retrieval Augmentation for Large Language Models

Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in large language models (LLMs) by injecting external knowledge into the context window, yet its effectiveness is rigidly constrained by attention dilution and inference cost. Existing knowledge-graph-enhanced methods follow a sequenti...

Zi-Hao Zhou, Gang Yin, Ze-Jian Lu et al. · 0 citations
Sep 2026

Efficient Dense Vector Search within Knowledge Graph Content Embeddings

QLever-Unified Indexed Vector Embedding Retrieval (QUIVER), an extension to QLever that adds native support for dense vector retrieval within RDF knowledge graphs, and implements three optimizations: engine-level registration of tensor functions, vocabulary-time parsing of JSON-encoded vectors, and a virtual SERVICE th...

Benedikt Kantz, Tobias Schreck, Gianmaria Silvello · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.