GitHub - belinwu/Awesome-GraphRAG: Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

Awesome-GraphRAG (GraphRAG Survey)

This repository contains a curated list of resources on graph-based retrieval-augmented generation (GraphRAG), which are classified according to "A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models". Continuously updating, stay tuned!

Overview of traditional RAG and two typical GraphRAG workflows.

  • Non-graph RAG organizes the corpus into chunks, ranks them by similarity, and retrieves the most relevant text for generating responses.
  • Knowledge-based GraphRAG extracts detailed knowledge graphs from the corpus using entity recognition and relation extraction, offering fine-grained, domain-specific information.
  • Index-based GraphRAG summarizes the corpus into high-level topic nodes, which are linked to form an index graph, while the fact linking maps topics to text.

RAG vs. GraphRAG

GraphRAG is a new paradigm of RAG that revolutionizes domain-specific LLM applications, by addressing traditional RAG limitations through three key innovations: (i) graph-structured knowledge representation that explicitly captures entity relationships and domain hierarchies, (ii) graph-aware retrieval mechanisms that enable multi-hop reasoning and context-preserving knowledge acquisition, and (iii) structure-guided knowledge search algorithms that ensure efficient retrieval across large-scale corpora.

Comparison between traditional RAG and GraphRAG.

📫 Contact Us

We welcome researchers to share related work to enrich this list or provide insightful comments on our survey. Feel free to reach out to the corresponding co-first authors: Qinggang Zhang, Shengyuan Chen.

Table of Content

📈 Trend of GraphRAG Research

The development trends in the field of GraphRAG with representative works.

📜 Research Papers

Knowledge Organization

Graphs for Knowledge Indexing

  • (arXiv 2025) DIGIMON: A unified and modular graph-based RAG framework [Paper]
  • (arXiv 2025) ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation [Paper]
  • (arXiv 2025) KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG [Paper]
  • (arXiv 2025) PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation [Paper]
  • (arXiv 2024) Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [Paper]
  • (arXiv 2024) KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation [Paper]
  • (arXiv 2024) OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models [Paper]
  • (arXiv 2024) GRAG: Graph Retrieval-Augmented Generation [Paper]
  • (arXiv 2024) Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning [Paper]
  • (ICLR 2024) RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval Paper
  • (AAAI 2024) Knowledge graph prompting for multi-document question answering [Paper]
  • (arXiv 2024) GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model [Paper]
  • (NeurIPS 2023) Avis: Autonomous visual information seeking with large language model agent [Paper]
  • (CoRL 2023) Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning [Paper]
  • (arXiv 2020) Answering complex open-domain questions with multi-hop dense retrieval [Paper]
  • (arXiv 2019) Knowledge guided text retrieval and reading for open domain question answering [Paper]

Graphs as Knowledge Carrier

Knowledge Graph Construction from Corpus

  • (arXiv 2025) MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot [Paper]
  • (arXiv 2025) PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths [Paper]
  • (arXiv 2024) From local to global: A graph rag approach to query-focused summarization [Paper]
  • (EMNLP 2024 )Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text [Paper]
  • (EMNLP 2024 Findings) GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models [Paper]
  • (SIGIR 2024) Retrieval-augmented generation with knowledge graphs for customer service question answering [Paper]
  • (arXiv 2024) DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generation [Paper]
  • (arXiv 2024) FastRAG: Retrieval Augmented Generation for Semi-structured Data [Paper]
  • (TechRxiv 2024) LuminiRAG: Vision-Enhanced Graph RAG for Complex Multi-Modal Document Understanding [Paper]
  • (BigData 2023) AutoKG: Efficient automated knowledge graph generation for language models [Paper]
  • (ACL 2019) Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs [Paper]
  • (SIGIR 2019) Answering complex questions by joining multi-document evidence with quasi knowledge graphs [Paper]

GraphRAG with Existing KGs

  • (ICLR 2025) Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation [Paper]
  • (arXiv 2024)StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization [Paper]
  • (ICLR 2024) Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning [Paper]
  • (AAAI 2024) Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting [Paper]
  • (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
  • (Bioinformatics 2024) Biomedical knowledge graph-enhanced prompt generation for large language models [Paper]
  • (NeurIPS 2024) KnowGPT: Knowledge Graph based PrompTing for Large Language Models [Paper]
  • (ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
  • (IEEE VIS 2024) KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration [Paper]
  • (CoLM 2024) ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction [Paper]
  • (arXiv 2024) LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration [Paper]
  • (arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]

Hybrid GraphRAG

  • (NAACL 2025) Knowledge Graph-Guided Retrieval Augmented Generation [Paper]
  • (ACL 2024 Findings) HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases[Paper]
  • (arXiv 2024) Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs [Paper]
  • (arXiv 2024) Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation [Paper]
  • (arXiv 2024) Codexgraph: Bridging large language models and code repositories via code graph databases [Paper]

Knowledge Retrieval

Semantics Similarity-based Retriever

  • (AAAI 2024) StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation [Paper]
  • (arXiv 2024) G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [Paper]
  • (arXiv 2024) CancerKG.ORG A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Care [Paper]
  • (arXiv 2024) Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning [Paper]
  • (arXiv 2024) GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model [Paper]
  • (arXiv 2024) Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation [Paper]
  • (arXiv 2024) How to Make LLMs Strong Node Classifiers? [Paper]

Logical Reasoning-based Retriever

  • (NeurIPS 2024) KnowGPT: Knowledge Graph based PrompTing for Large Language Models [Paper]
  • (ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
  • (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
  • (CIKM 2024) RD-P: A Trustworthy Retrieval-Augmented Prompter with Knowledge Graphs for LLMs [Paper]
  • (arXiv 2024) RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering [Paper]
  • (LHB 2024) Intelligent question answering for water conservancy project inspection driven by knowledge graph and large language model collaboration [Paper]
  • (arXiv 2024) RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs [Paper]

LLM-based Retriever

  • (AAAI 2024) Knowledge graph prompting for multi-document question answering [Paper]
  • (EMNLP 2024 )Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text [Paper]
  • (ACML) Enhancing Textbook Question Answering with Knowledge Graph-Augmented Large Language Models [Paper]
  • (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
  • (arXiv 2024) LightRAG: Simple and Fast Retrieval-Augmented Generation [Paper]
  • (arXiv 2024) MEG: Medical Knowledge-Augmented Large Language Models for Question Answering [Paper]
  • (arXiv 2024) From local to global: A graph rag approach to query-focused summarization [Paper]

GNN-based Retriever

  • (arXiv 2025) CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs [Paper]
  • (arXiv 2024) Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation [Paper]
  • (arXiv 2024) Language Models are Graph Learners [Paper]
  • (arXiv 2024) Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [Paper]
  • (arXiv 2024) Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation [Paper]

Multi-round Retriever

  • (arXiv 2024) Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [Paper]
  • (arXiv 2024) Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation [Paper]
  • (arXiv 2024) Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs [Paper]

Post-retrieval

  • (ACL 2024) Boosting Language Models Reasoning with Chain-of-Knowledge Prompting [Paper]
  • (ACL Findings 2024) Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments [Paper]
  • (arXiv 2024) Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models [Paper]
  • (arXiv 2024) Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting [Paper]

Hybrid Retriever

  • (arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]
  • (arXiv 2024) StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization [Paper]

Knowledge Integration

Fine-tuning

Fine-tuning with Node-level Knowledge

  • (arXiv 2025) Large Language Models based Graph Convolution for Text-Attributed Networks? [Paper]
  • (SIGIR 2024) Graphgpt: Graph instruction tuning for large language models [Paper]

Fine-tuning with Path-level Knowledge

  • (AAAI 2024) Exploring large language model for graph data understanding in online job recommendations [Paper]
  • (arXiv 2024) MuseGraph: Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining [Paper]
  • (WWW 2023) Structure pretraining and prompt tuning for knowledge graph transfer [Paper]
  • (ICLR 2023) Reasoning on graphs: Faithful and interpretable large language model reasoning [Paper]

Fine-tuning with Subgraph-level Knowledge

  • (ICML 2024) Llaga: Large language and graph assistant [Paper]
  • (KDD 2024) Graphwiz: An instruction-following language model for graph problems [Paper]
  • (AAAI 2024) Graph neural prompting with large language models [Paper]
  • (ACL 2024 Findings) Rho:Reducing hallucination in open-domain dialogues with knowledge grounding [Paper]
  • (EACL 2024 Findings) Language is All a Graph Needs [Paper]

In-context Learning

Graph-enhanced Chain-of-Thought

  • (KBS 2025) Different paths to the same destination: Diversifying LLMs generation for multi-hop open-domain question answering [Paper]
  • (ICLR 2024) Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning [Paper]
  • (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
  • (arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]
  • (arXiv 2024) Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [Paper]
  • (ICLR 2024) Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources [Paper]
  • (ACL Finding 2024) Visual In-Context Learning for Large Vision-Language Models [Paper]
  • (NeurIPS 2023) What makes good examples for visual in-context learning? [Paper]
  • (ACL 2023) Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models [Paper]
  • (AAAI 2024) When Do Program-of-Thought Works for Reasoning? [Paper]
  • (ICLR 2022) An Explanation of In-context Learning as Implicit Bayesian Inference [Paper]
  • (EMNLP 2023) KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases [Paper]

Collaborative Knowledge Graph Refinement

  • (AAAI 2024) Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting [Paper]
  • (ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
  • (arXiv 2024) Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs [Paper]
  • (arXiv 2024) Explore then Determine: A GNN-LLM Synergy Framework for Reasoning over Knowledge Graph [Paper]
  • (ACL 2024) CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph [Paper]

📚 Related Survey Papers

  • (arXiv 2025) Retrieval-Augmented Generation with Graphs (GraphRAG) [Paper]
  • (arXiv 2024) Graph Retrieval-Augmented Generation: A Survey [Paper]
  • (AIxSET 2024) Graph Retrieval-Augmented Generation for Large Language Models: A Survey [Paper]

To explore the applications of LLMs on graph tasks, we recommend the following repositories:

🏆 Benchmarks

Dataset Task Paper Repo
DIGIMON Large-scale graphRAG [arXiv 2025] [Github]
SimpleQuestion Simple Question Answering [arXiv 2015] [Github]
WebQ Simple Question Answering [EMNLP 2013] [CodaLab]
Multihop-RAG Multi-hop Reasoning [COLING 2024] [Github]
CWQ Multi-hop Reasoning [NAACL 2018] [TAU-NLP]
MetaQA Multi-hop Reasoning [AAAI 2018] [Github]
MetaQA-3 Multi-hop Reasoning [AAAI 2018] [Github]
CURD Large-scale Complex QA [arXiv 2024] [Github]
KQAPro Large-scale Complex QA [ACL 2022] [Github]
LC-QuAD v2 Large-scale Complex QA [ISWC 2019] [figshare]
LC-QuAD Large-scale Complex QA [ISWC 2017] [Github]
UltraDomain Domain-specific QA [arXiv 2024] [Github]
TutorQA Domain-specific QA [arXiv 2024] [Github]
FACTKG Domain-specific QA [ACL 2023] [Github]
Mintaka Domain-specific QA [ACL 2022] [Github]
GrailQA Domain-specific QA [WWW 2021] [Github]
WebQSP Domain-specific QA [ACL 2016] [Microsoft]

💻 Open-source Projects

  • GitHub DIGIMON: A unified and modular graph-based RAG framework
  • GitHub Microsoft-GraphRAG: A modular graph-based Retrieval-Augmented Generation (RAG) system
  • GitHub Nano-GraphRAG: A simple, easy-to-hack GraphRAG implementation
  • GitHub Fast GraphRAG: RAG that intelligently adapts to your use case, data, and queries
  • GitHub LightRAG: Simple and Fast Retrieval-Augmented Generation
  • GitHub HuixiangDou2: A Robustly Optimized GraphRAG Approach
  • GitHub GraphRAG-SDK: a specialized toolkit for building GraphRAG systems.

🍀 Citation

If you find this survey helpful, please cite our paper:

@article{zhang2025survey,
  title={A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models},
  author={Zhang, Qinggang and Chen, Shengyuan and Bei, Yuanchen and Yuan, Zheng and Zhou, Huachi and Hong, Zijin and Dong, Junnan and Chen, Hao and Chang, Yi and Huang, Xiao},
  journal={arXiv preprint arXiv:2501.13958},
  year={2025}
}

⭐ Star History

Star History Chart