A Survey on Graph-Based Retrieval-Augmented Generation: Architectures, Methods, and Applications
DOI:
https://doi.org/10.63503/j.ijcma.2026.235Keywords:
Retrieval-Augmented Generation, Graph-RAG, Knowledge Graphs, Hybrid Retrieval, Explainable AI.Abstract
Retrieval-Augmented Generation (RAG) stands out as a promising paradigm that can be applied to improve large language models by serving text generation with external sources of knowledge. Nevertheless, traditional RAG models are mostly based on flat text corpora and similarity-based retrieval and thus are not able to realize intricate relations, multi-hop dependencies, and structured semantics. The survey provides a high-level introduction to graph-based Retrieval-Augmented Generation (Graph-RAG), which is an emerging methodology adding systematic knowledge representations to the retrieval and generation process. Graph-RAG supports relational knowledge reasoning, contextual cohesion and explicit dependency modeling, complementary to text-only retrieval by organizing knowledge into graphs e.g., knowledge graphs, citation networks, and semantic graphs. The survey discusses the principles underlying RAG, gives a description of the weaknesses of the vector-based and token-based retrieval frameworks, and explains how the graph-aware architecture overcomes these weaknesses. Graph-RAG methods are systematically classified based on the architectural design options, retrieval schemes, learning methods, and reasoning methods, such as graph neural networks, hybrid graph-vector retrieval, and multi-hop inference. The main areas of application including healthcare, finance, and scientific question answering are discussed, and their areas are improved in factual grounding, interpretability, and robustness. Lastly, there are open issues that are concerned with scalability, graph dynamic updates, interpretability, and evaluation.
References
[1] Y. Hu, Z. Lei, Z. Zhang, B. Pan, C. Ling, and L. Zhao, “GRAG: Graph retrieval-augmented generation,” arXiv preprint arXiv:2405.16506, 2024.
[2] M. Arslan, S. Munawar, and C. Cruz, “Business insights using RAG–LLMs: A review and case study,” J. Decis. Syst., pp. 1–30, Oct. 2024, doi: 10.1080/12460125.2024.2410040.
[3] S. Ji, S. Pan, E. Cambria, P. Marttinen, and P. S. Yu, “A survey on knowledge graphs: Representation, acquisition, and applications,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 2, pp. 494–514, Feb. 2021, doi: 10.1109/TNNLS.2021.3070843.
[4] Y. Liu, X. Zhang, Y. Li, J. Zhou, X. Li, and G. Zhao, “Graph-based facial affect analysis: A review,” IEEE Trans. Affect. Comput., vol. 14, no. 4, pp. 2657–2677, Oct. 2023, doi: 10.1109/TAFFC.2022.3215918.
[5] Makarov, D. Kiselev, N. Nikitinsky, and L. Subelj, “Survey on graph embeddings and their applications to machine learning problems on graphs,” PeerJ Comput. Sci., vol. 7, p. e357, Feb. 2021, doi: 10.7717/peerj-cs.357.
[6] L. Zhong, J. Wu, Q. Li, H. Peng, and X. Wu, “A comprehensive survey on automatic knowledge graph construction,” ACM Comput. Surv., vol. 56, no. 4, pp. 1–62, Apr. 2023, doi: 10.1145/3618295.
[7] L. Waikhom and R. Patgiri, “Graph neural networks: Methods, applications, and opportunities,” arXiv preprint arXiv:2108.10733, 2021.
[8] L. Wang, C. Sun, C. Zhang, W. Nie, and K. Huang, “Application of knowledge graph in software engineering field: A systematic literature review,” Inf. Softw. Technol., vol. 164, p. 107327, Dec. 2023, doi: 10.1016/j.infsof.2023.107327.
[9] V. Hassija et al., “Interpreting black-box models: A review on explainable artificial intelligence,” Cognit. Comput., vol. 16, no. 1, pp. 45–74, Jan. 2024, doi: 10.1007/s12559-023-10179-8.
[10] M. S. Wajid, H. Terashima-Marin, P. Najafirad, and M. A. Wajid, “Deep learning and knowledge graph for image/video captioning: A review of datasets, evaluation metrics, and methods,” Eng. Rep., vol. 6, no. 1, Jan. 2024, doi: 10.1002/eng2.12785.
[11] M. J. Buehler, “Generative retrieval-augmented ontologic graph and multiagent strategies for interpretive large language model-based materials design,” ACS Eng. Au, vol. 4, no. 2, pp. 241–277, Apr. 2024, doi: 10.1021/acsengineeringau.3c00058.
[12] L. Opdahl et al., “Semantic knowledge graphs for the news: A review,” ACM Comput. Surv., vol. 55, no. 7, pp. 1–38, Jul. 2023, doi: 10.1145/3543508.
[13] X. Zhang, Y. Zhou, and J. Luo, “Deep learning for processing and analysis of remote sensing big data: A technical review,” Big Earth Data, vol. 6, no. 4, pp. 527–560, Oct. 2022, doi: 10.1080/20964471.2021.1964879.
[14] V. Pal and S. K. Chintagunta, “Transformer-based graph neural networks for real-time fraud detection in blockchain networks,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 3, pp. 1401–1411, Jul. 2023, doi: 10.48175/IJARSCT-11978Y.
[15] V. T. Hoang et al., “Graph representation learning and its applications: A survey,” Sensors, vol. 23, no. 8, p. 4168, Apr. 2023, doi: 10.3390/s23084168.
[16] L. Alzubaidi et al., “Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, p. 53, 2021, doi: 10.1186/s40537-021-00444-8.
[17] Y. Sha et al., “Retrieval-augmented knowledge graph reasoning for commonsense question answering,” Mathematics, 2023, doi: 10.3390/math11153269.
[18] G. Sarraf, “Privacy preserving blockchain for healthcare: Addressing security challenges through decentralized architecture,” Tech. Int. J. Eng. Res., vol. 10, no. 11, pp. 111–117, 2023, doi: 10.56975/tijer.v10i11.159993.
[19] E. Watson, T. Viana, and S. Zhang, “Augmented behavioral annotation tools, with application to multimodal datasets and models: A systematic review,” AI, vol. 4, no. 1, pp. 128–171, Jan. 2023, doi: 10.3390/ai4010007.
[20] P. Chandrashekar, “A survey of tools, techniques, and best practices: CI/CD integration in DevOps workflows,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 3, pp. 1366–1376, Jul. 2023, doi: 10.48175/IJARSCT-11978V.
[21] S. Garg, “Predictive analytics and auto remediation using artificial intelligence and machine learning in cloud computing operations,” Int. J. Innov. Res. Eng. Multidiscip. Phys. Sci., vol. 7, no. 2, 2019.
[22] W. Fan et al., “A survey on RAG meeting LLMs: Towards retrieval-augmented large language models,” in Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2024, pp. 6491–6501, doi: 10.1145/3637528.3671470.
[23] P. Zhao et al., “Retrieval-augmented generation for AI-generated content: A survey,” arXiv preprint, Jun. 2024.
[24] C. Gao et al., “A survey of graph neural networks for recommender systems: Challenges, methods, and directions,” ACM Trans. Recomm. Syst., vol. 1, no. 1, pp. 1–51, Mar. 2023, doi: 10.1145/3568022.
[25] L. Opdahl et al., “Semantic knowledge graphs for the news: A review,” ACM Comput. Surv., vol. 55, no. 7, pp. 1–38, Jul. 2022, doi: 10.1145/3543508.
