Elamur Research⌕
☰
home / papers / 2025 / Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation

Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation

Paper · 2025 · Shijie Wang, Wenqi Fan, Yue Feng et al.

Summary

LLM-based recommenders often hallucinate, for example by suggesting films that do not exist. They also lack recent and domain-specific knowledge, and retraining them often is expensive. Standard document-based RAG can help, but it brings in noisy text and ignores how entities relate to each other. The authors propose K-RagRec, which pulls structured, up-to-date knowledge from an item knowledge graph (Freebase) to support a frozen LLM. The pipeline has four stages:

  1. Indexing. Item KG sub-graphs are indexed at coarse and fine granularity using a GNN and a PLM, producing a vector database.
  2. Selective retrieval. A popularity-based policy decides which items need retrieval at all.
  3. Re-ranking. Retrieved sub-graphs are re-ranked so the most relevant ones come first.
  4. Encoding. A GNN plus a projector maps the sub-graphs into the LLM's embedding space, so the graph is not serialized into long text.

The task is choosing a user's preferred item from a candidate set. On three real-world datasets, including MovieLens-1M and Amazon Book, K-RagRec beats KG-based RAG baselines in accuracy. It also stays nearly as fast as inference without retrieval. This makes graph-structured RAG a practical alternative to frequent fine-tuning.

Key points

  • Architecture: hop-field knowledge sub-graph indexing, a popularity selective retrieval policy, sub-graph re-ranking, and GNN-based encoding into a frozen LLM. The main backbone is LLama-2-7b, and only 7b/8b models were tested.
  • Accuracy (MovieLens-1M, LLama-2-7b): K-RagRec reaches 0.429, while the best baselines (GraphToken, G-Retriever) reach about 0.27. KG-Text and KAPING stay below 0.08.
  • Inference time: about 1.06 s per query for K-RagRec versus 0.92 s without RAG. KG RAG baselines take 2.19–6.47 s. Timing was measured on two NVIDIA A6000 GPUs.
  • Hyperparameters: K = 3 retrieved sub-graphs and p = 50% popularity threshold. N = 5–7 re-ranked sub-graphs works best on Amazon Book. Inference time grows roughly linearly with p.
  • Limitations noted by the authors: Freebase is the only KG used. Future work includes larger LLMs, other KGs (YAGO, DBpedia, Wikipedia), and adaptive retrieval policies such as reinforcement learning.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢BaiduBeijing · China74 works · 15,263 citations🎓Hong Kong Polytechnic UniversityHong Kong · China84 works · 4,956 citations🎓University of BirminghamBirmingham · United Kingdom25 works · 62,564 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 works

🧭 Topics 2Research subjects and languages the work is about.Information retrieval & search · 473 worksKnowledge graphs & ontologies · 192 works

Cite

Cite as Shijie Wang, Wenqi Fan, Yue Feng, Lin Shanru, Xinyu Ma, Shuaiqiang Wang and Dawei Yin. 2025. Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.1317

@inproceedings{wang2025knowledge,
  title = {{Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation}},
  author = {Shijie Wang, Wenqi Fan, Yue Feng, Lin Shanru, Xinyu Ma, Shuaiqiang Wang and Dawei Yin},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.1317},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1317}
}

References

52 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2017. Controlling popularity bias in learning-to-rank recommendation. In Proceedings of the eleventh ACM conference on recommender systems, pages 42–46. find
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  3. Yihao Ang, Yifan Bao, Qiang Huang, Anthony KH Tung, and Zhiyong Huang. 2024. Tsgassist: An interactive assistant harnessing llms and rag for time series generation recommendations and benchmarking. Proceedings of the VLDB Endowment, 17(12):4309– 4312. find
  4. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. arXiv preprint arXiv:2310.11511.
  5. Jinheon Baek, Alham Fikri Aji, and Amir Saffari. 2023. Knowledge-augmented language model prompting for zero-shot knowledge graph question answering. arXiv preprint arXiv:2306.04136.
  6. Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1007–1014. find
  7. Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. In International conference on machine learn… find
  8. Òscar Celma and Perfecto Herrera. 2008. A new approach to evaluating novel recommendations. In Proceedings of the 2008 ACM conference on Recommender systems, pages 179–186. find
  9. Dario Di Palma. 2023. Retrieval-augmented recommender system: Enhancing recommender systems with large language models. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1369–1373. find
  10. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  11. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024a. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6491– 6501.
  12. Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In The world wide web conference, pages 417–426. find
  13. Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, et al. 2024b. Graph machine learning in the era of large language models (llms). arXiv preprint arXiv:2404.14928. — [arXiv:2404.14928](https://arxiv.org/abs/2404.14928) find
  14. Bahare Fatemi, Jonathan Halcrow, and Bryan Perozzi. 2023. Talk like a graph: Encoding graphs for large language models. arXiv preprint arXiv:2310.04560. find
  15. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
  16. Shijie Geng, Shuchang Liu, Zuohui Fu, Yingqiang Ge, and Yongfeng Zhang. 2022. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5). In Proceedings of the 16th ACM Conference on Recommender Systems, pages 299–315. find
  17. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning, pages 3929–3938. PMLR.
  18. Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
  19. Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 639–648. find
  20. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. arXiv preprint arXiv:2402.07630.
  21. Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. 2022. Towards universal sequence representation learning for recommender systems. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 585–593. find
  22. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
  23. Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Active retrieval augmented generation. arXiv preprint arXiv:2305.06983.
  24. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906.
  25. Krishnaram Kenthapadi, Benjamin Le, and Ganesh Venkataraman. 2017. Personalized job recommendation system at linkedin: Practical challenges and lessons learned. In Proceedings of the eleventh ACM conference on recommender systems, pages 346–347. find
  26. Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172. find
  27. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  28. Tiziano Labruna, Jon Ander Campos, and Gorka Azkune. 2024. When to retrieve: Teaching llms to utilize information retrieval effectively. arXiv preprint arXiv:2404.19705. find
  29. Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, and Qing Li. 2024. Empowering molecule discovery for molecule-caption translation with large language models: A chatgpt perspective. IEEE Transactions on Knowledge and Data Engineering. find
  30. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2023. Reasoning on graphs: Faithful and interpretable large language model reasoning. arXiv preprint arXiv:2310.01061. find
  31. Costas Mavromatis and George Karypis. 2024. Gnn-rag: Graph neural retrieval for large language model reasoning. arXiv preprint arXiv:2405.20139. find
  32. Sewon Min, Julian Michael, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2020. Ambigqa: Answering ambiguous open-domain questions. arXiv preprint arXiv:2004.10645. find
  33. Bryan Perozzi, Bahare Fatemi, Dustin Zelle, Anton Tsitsulin, Mehran Kazemi, Rami Al-Rfou, and Jonathan Halcrow. 2024. Let your graph do the talking: Encoding structured data for llms. arXiv preprint arXiv:2402.05862. — [arXiv:2402.05862](https://arxiv.org/abs/2402.05862) find
  34. Haohao Qu, Wenqi Fan, Zihuai Zhao, and Qing Li. 2024. Tokenrec: Learning to tokenize id for llm-based generative recommendation. arXiv preprint arXiv:2406.10450. — [arXiv:2406.10450](https://arxiv.org/abs/2406.10450) find
  35. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11:1316–1331.
  36. Yike Wu, Nan Hu, Sheng Bi, Guilin Qi, Jie Ren, Anhuan Xie, and Wei Song. 2023b. Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. arXiv preprint arXiv:2309.11206. find
  37. N Reimers. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  38. Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, and Zhen-Hua Ling. 2024. Corrective retrieval augmented generation. arXiv preprint arXiv:2401.15884.
  39. Priyanka Sen, Sandeep Mavadia, and Amir Saffari. 2023. Knowledge graph-augmented language models for complex question answering. In Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE), pages 1–8. find
  40. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. find
  41. Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjin Wang, and Yu Sun. 2020. Masked label prediction: Unified message passing model for semi-supervised classification. arXiv preprint arXiv:2009.03509. — [arXiv:2009.03509](https://arxiv.org/abs/2009.03509) find
  42. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Heung-Yeung Shum, and Jian Guo. 2023. Think-on-graph: Deep and responsible reasoning of large language model with knowledge graph. arXiv preprint arXiv:2307.07697. find
  43. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  44. Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio, et al. 2017. Graph attention networks. stat, 1050(20):10– 48550. find
  45. Junjie Zhang, Yupeng Hou, Ruobing Xie, Wenqi Sun, Julian McAuley, Wayne Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2024. Agentcf: Collaborative learning with autonomous language agents for recommender systems. In Proceedings of the ACM on Web Conference 2024, pages 3679–3689. find
  46. Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, and Xiangnan He. 2023. Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488. — [arXiv:2310.19488](https://arxiv.org/abs/2310.19488) find
  47. Jujia Zhao, Wenjie Wang, Xinyu Lin, Leigang Qu, Jizhi Zhang, and Tat-Seng Chua. 2023. Popularity-aware distributionally robust optimization for recommendation system. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4967–4973. find
  48. Zihuai Zhao, Wenqi Fan, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Zhen Wen, Fei Wang, Xiangyu Zhao, Jiliang Tang, et al. 2024. Recommender systems in the era of large language models (llms). IEEE Transactions on Knowledge and Data Engineering. find
  49. Keheng Wang, Feiyu Duan, Sirui Wang, Peiguang Li, Yunsen Xian, Chuantao Yin, Wenge Rong, and Zhang Xiong. 2023. Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering. arXiv preprint arXiv:2308.13259. — [arXiv:2308.13259](https://arxiv.org/abs/2308.13259) find
  50. Wei Wei, Xubin Ren, Jiabin Tang, Qinyong Wang, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, and Chao Huang. 2024. Llmrec: Large language models with graph augmentation for recommendation. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 806–815. find
  51. Junda Wu, Cheng-Chun Chang, Tong Yu, Zhankui He, Jianing Wang, Yupeng Hou, and Julian McAuley. 2024. Coral: Collaborative retrieval-augmented large language models improve long-tail recommendation. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3391–34… find
  52. Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2023a. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2025-knowledge-graph-retrieval-augmented-generation/