mlsanityData to 14 Oct 2026

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

arXiv 2607.28397 ↗First posted 30 Jul 2026cs.AI cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 33 of its 53 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

33 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation10 Sep
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  3. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
18 more
  1. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  2. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  3. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  4. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  5. 2020Investigating Pretrained Language Models for Graph-to-Text Generationcited by 117
  6. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  7. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 56
  8. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answeringcited by 43
  9. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  10. 2019The TechQA Datasetcited by 30
  11. 2021Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Modelscited by 29
  12. 2021Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Frameworkcited by 21
  13. 2025Set-LLM: A Permutation-Invariant LLMcited by 11
  14. 2022Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevancecited by 10
  15. 2025G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledgecited by 9
  16. 2023Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Taskscited by 6
  17. 2026Teaching LLMs to See Graphs: Unifying Text and Structural Reasoningcited by 2
  18. 2026When Graph Language Models Go Beyond Memorizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
  2. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
  3. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
  4. 2025Query-Centric Graph Retrieval Augmented Generation
  5. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  6. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  7. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
  8. 2025Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering