GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation

arXiv:2607.28397v1 Announce Type: cross Abstract: 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.

Related

• In-depth Analysis of Graph-based RAG in a Unified Framework
• MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation
• Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
• Structure Over Scale: Schema-Constrained Causal Graphs for RAG
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs

Source: arXiv cs.CL | 2026-07-31