Graph-based retrieval-augmented generation (GraphRAG) leverages knowledge graphs to provide context for large language models (LLMs) to generate quality responses. Yet existing GraphRAG methods suffer from two drawbacks: connecting each entity to all passages that mention the entity causes one-to-many entity-passage mapping problem and retrieves redundant passages, and fixed graph traversal patterns fail to locate target information for hard queries. To tackle the two limitations, we propose PoP-RAG, which features a passage-on-edge (PoE) graph that links the passages with graph edges to resolve the one-to-many entity-passage mapping problem. PoP-RAG further introduces a query planning step that decomposes a query into sub-queries and builds a directed acyclic graph (DAG) to model their relationships. This design enables targeted retrieval for each sub-query and ensures transparent response derivation logic, thus enhancing explainability. Experimental results demonstrate that PoP-RAG outperforms existing GraphRAG methods, especially on complex queries.
- Open Access
- Article
PoP-RAG: Holistic Query Planning for GraphRAG
- Qiming Zeng 1,
- Xintong Hu 1,
- Yuhao Lin 1,
- Hao Luo 1,
- Susie Xi Rao 2,
- Xiao Yan 1,
- Jiawei Jiang 1,*
Author Information
Received: 18 May 2026 | Revised: 06 Sep 2026 | Accepted: 11 Sep 2026 | Published: 22 Sep 2026
Abstract
References
- 1.
Touvron, H.; Martin, L.; Stone, K.; et al. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv 2023, arXiv:2307.09288.
- 2.
Achiam, J.; Adler, S.; Agarwal, S.; et al. GPT-4 Technical Report. arXiv 2023, arXiv:2303.08774.
- 3.
Bai, J.; Bai, S.; Chu, Y.; et al. Qwen technical report. arXiv 2023, arXiv:2309.16609.
- 4.
Chen, J.; Liu, Z.; Huang, X.; et al. When large language models meet personalization: Perspectives of challenges and opportunities. World Wide Web 2024, 27, 42.
- 5.
Hadi. MU.; Qureshi, R.; Shah, A.; et al. Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects. Authorea Prepr. 2023, 1, 1–26.
- 6.
Tan, Y.; Min, D.; Li, Y.; et al. Can ChatGPT replace traditional KBQA models? An in-depth analysis of the question answering performance of the GPT LLM family. In Proceedings of the International Semantic Web Conference, Athens, Greece, 6–10 November 2023; Springer: Cham, Switzerland, 2023; pp. 348–367.
- 7.
Yang, J.; Jin, H.; Tang, R.; et al. Harnessing the Power of Llms in Practice: A Survey on ChatGPT and Beyond. arXiv 2023, arXiv:2304.13712.
- 8.
Yu, X.; Zhang, Z.; Niu, F.; et al. What Makes a High-Quality Training Dataset for Large Language Models: A Practitioners’ Perspective. In Proceedings of the IEEE/ACM International Conference on Automated Software Engineering, Sacramento, CA, USA, 27 October–1 November 2024; pp. 656–668.
- 9.
Villalobos, P.; Ho, A.; Sevilla, J.; et al. Will we run out of data? Limits of LLM scaling based on human-generated data. arXiv 2022, arXiv:2211.04325.
- 10.
Ji, Z.; Yu, T.; Xu, Y.; et al. Towards mitigating LLM hallucination via self reflection. In Proceedings of the Findings of the Association for Computational Linguistics: EMNLP, Singapore, 6–10 December 2023; pp. 1827–1843.
- 11.
Friel, R.; Sanyal, A. Chainpoll: A high efficacy method for LLM hallucination detection. arXiv 2023, arXiv:2310.18344.
- 12.
McDonald, D.; Papadopoulos, R.; Benningfield, L. Reducing llm hallucination using knowledge distillation: A case study with mistral large and mmlu benchmark. Authorea Prepr. 2024. https://doi.org/10.36227/techrxiv.171665607.76504195/v1.
- 13.
Lewis, P.; Perez, E.; Piktus, A.; et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural Inf. Process. Syst. 2020, 33, 9459–9474.
- 14.
Gao, Y.; Xiong, Y.; Gao, X.; et al. Retrieval-augmented generation for large language models: A survey. arXiv 2023, arXiv:2312.10997.
- 15.
Siriwardhana, S.; Weerasekera, R.; Wen, E.; et al. Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Trans. Assoc. Comput. Linguist. 2023, 11, 1–17.
- 16.
Arslan, M.; Ghanem, H.; Munawar, S.; et al. A Survey on RAG with LLMs. Procedia Comput. Sci. 2024, 246, 3781–3790.
- 17.
Fan, W.; Ding, Y.; Ning, L.; et al. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, 25–29 August 2024; pp. 6491–6501.
- 18.
Zhang, Q.; Chen, S.; Bei, Y.; et al. A survey of graph retrieval-augmented generation for customized large language models. arXiv 2025, arXiv:2501.13958.
- 19.
Procko, T.T.; Ochoa, O. Graph retrieval-augmented generation for large language models: A survey. In Proceedings of the 2024 Conference onAI, Science, Engineering, and Technology (AIxSET), LagunaHills, CA,USA, 30 September 2024–2 October 2024; pp. 166–169.
- 20.
Boccaletti, S.; Latora, V.; Moreno, Y.; et al. Complex networks: Structure and dynamics. Phys. Rep. 2006, 424, 175–308.
- 21.
Peng, B.; Zhu, Y.; Liu, Y.; et al. Graph retrieval-augmented generation: A survey. arXiv 2024, arXiv:2408.08921.
- 22.
Jimenez Gutierrez, B.; Shu, Y.; Gu, Y.; et al. Hipporag: Neurobiologically inspired long-term memory for large language models. Adv. Neural Inf. Process. Syst. 2024, 37, 59532–59569.
- 23.
Han, H.; Wang, Y.; Shomer, H.; et al. Retrieval-augmented generation with graphs (graphRAG). arXiv 2024, arXiv:2501.00309.
- 24.
Edge, D.; Trinh, H.; Cheng, N.; et al. From local to global: A graph rag approach to query-focused summarization. arXiv 2024, arXiv:2404.16130.
- 25.
Guo, Z.; Xia, L.; Yu, Y.; et al. LightRAG: Simple and fast retrieval-augmented generation. arXiv 2024, arXiv:2410.05779.
- 26.
Gutiérrez, B.J.; Shu, Y.; Qi, W.; et al. From RAG to Memory: Non-Parametric Continual Learning for Large Language Models. In Proceedings of the Forty-Second International Conference on Machine Learning, Vancouver, BC, Canada, 13–19 July 2025.
- 27.
Sun, J.; Xu, C.; Tang, L.; et al. Think-on-Graph: Deep and Responsible Reasoning of Large LanguageModel onKnowledgeGraph. In Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria, 7–11 May 2024.
- 28.
Jin, B.; Xie, C.; Zhang, J.; et al. Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs. In Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand, 11–16 August 2024; pp. 163–184.
- 29.
Wang, S.; Sun, X.; Li, X.; et al. GPT-ner: Named entity recognition via large language models. In Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, NM, USA, 29 April–4 May 2025; pp. 4257–4275.
- 30.
Kolluru, K.; Adlakha, V.; Aggarwal, S.; et al. OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction. arXiv 2020, arXiv:2010.03147.
- 31.
Fischer, A.; Greiff, S.; Funke, J. The Process of Solving Complex Problems. J. Probl. Solving 2011, 4, 19–42.
- 32.
Tversky, A.; Kahneman, D. Utility, Probability, and Human Decision Making. Science 1974, 185, 1124–1131.
- 33.
Ho, X.; Nguyen, A.K.D.; Sugawara, S.; et al. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps. arXiv 2020, arXiv:2011.01060.
- 34.
Trivedi, H.; Balasubramanian, N.; Khot, T.; et al. MuSiQue: Multihop Questions via Single-hop Question Composition. Trans. Assoc. Comput. Linguist. 2022, 10, 539–554.
- 35.
Yang, Z.; Qi, P.; Zhang, S.; et al. HotpotQA: A dataset for diverse, explainable multi-hop question answering. arXiv 2018, arXiv:1809.09600.
- 36.
Press, O.; Zhang, M.; Min, S.; et al. Measuring and Narrowing the Compositionality Gap in Language Models. In Proceedings of the Findings of the Association for Computational Linguistics: EMNLP, Singapore, 6–10 December 2023; pp. 5687–5711.
- 37.
Trivedi, H.; Balasubramanian, N.; Khot, T.; et al. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada, 9–14 July 2023; pp. 10014–10037.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com