---
title: "Structure Guided Retrieval-Augmented Generation for Factual"
description: "For evaluation, the authors release ERQA, a 120,000-pair multi-constraint QA benchmark spanning 20 domains in… 61% F1. 51 references."
authors: ["Miao Xie", "Xiao Zhang", "Yi Li", "Chunli Lv"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1873/"
doi: "10.18653/v1/2026.acl-long.1873"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/xie-2026-structure-guided-retrieval-augmented-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xie-2026-structure-guided-retrieval-augmented-generation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/50/) / Structure Guided Retrieval-Augmented Generation for Factual Queries

# Structure Guided Retrieval-Augmented Generation for Factual Queries

**Authors:** Miao Xie, [Xiao Zhang](https://md.research.elamur.ai/free/en/authors/xiao-zhang/), [Yi Li](https://md.research.elamur.ai/free/en/authors/yi-li/) and Chunli Lv · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1873/) · [PDF](https://aclanthology.org/2026.acl-long.1873.pdf) · [DOI 10.18653/v1/2026.acl-long.1873](https://doi.org/10.18653/v1/2026.acl-long.1873) · [OpenAlex](https://openalex.org/W7166841918)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Standard RAG pipelines rank evidence by vector similarity, so they often miss part of the support needed for factual questions that combine several conditions. A typical example is asking which disease fits four separate clinical facts at once. The authors formalise this setting as the Exact Retrieval Problem (ERP): find knowledge that satisfies every constraint in a query, then use it to ground the LLM's answer. Their solution, SG-RAG, does three things:
- converts the document collection into a knowledge graph;
- turns the question into a small query graph;
- treats retrieval as approximate subgraph matching, using GNN-learned path dominance embeddings to avoid costly exact isomorphism search.

The matched subgraphs are then rewritten as fact lists in the prompt. For evaluation, the authors release ERQA, a 120,000-pair multi-constraint QA benchmark spanning 20 domains in English and Chinese. SG-RAG beats strong RAG baselines by large margins and adds only modest runtime cost. This matters because it shows that explicit structure, not just semantic closeness, is key for precise retrieval in domains such as medicine.

## Key points
- **ERQA subsets.** The benchmark has three parts:
  - FB-ERQA: 80,000 queries from an English encyclopedic graph.
  - UD-ERQA: 10,000 queries from English textbooks covering 18 domains.
  - CM-ERQA: 30,000 queries from a Chinese medical knowledge graph.
- **Headline results.** SG-RAG improves on baselines by 20.68–50.88 absolute percentage points, about 34% to over 450% in relative terms. The comparison includes NaiveRAG, GraphRAG, LightRAG, RAPTOR, KAG and others.
- **Comparison with simple retrieval (CM-ERQA).** SG-RAG reaches roughly 61% F1. Entity-based, 1-hop and 2-hop neighbourhood retrieval all stay near 11–12% F1.
- **Single-constraint queries (NQ).** SG-RAG still ranks first, with 89.33% Hit@1 and 89.41% F1, slightly ahead of LightRAG.
- **Efficiency.** Offline indexing on CM-ERQA takes about 11 h, versus 10 h for LightRAG and 8 h for GraphRAG. Online latency stays close to NaiveRAG. Results remain stable across generator LLMs such as GPT-4o-mini, GLM-4-Flash and Qwen-3.
- **Availability.** Code and data are public at github.com/CAU-X-AI-Lab.

*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

- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 184 works · 27,484 citations
- [China Agricultural University](https://md.research.elamur.ai/free/en/universities/china-agricultural-university/) — University, Beijing, China · 4 works · 17 citations

Also on the byline: [Ministry of Agriculture and Rural Affairs](https://ror.org/05ckt8b96).

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Miao Xie, Xiao Zhang, Yi Li and Chunli Lv. 2026. Structure Guided Retrieval-Augmented Generation for Factual Queries. Proceedings of the 64th 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.

```bibtex
@inproceedings{xie2026structure,
  title = {{Structure Guided Retrieval-Augmented Generation for Factual Queries}},
  author = {Miao Xie, Xiao Zhang, Yi Li and Chunli Lv},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1873},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1873}
}
```

- [← previous StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://md.research.elamur.ai/free/en/papers/xu-2026-structmem-structured-memory-long-horizon/)
- [next → Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External Knowledge](https://md.research.elamur.ai/free/en/papers/xu-2026-structure-aware-zero-shot-relational/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/50/)

## References

51 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Christopher R Aberger, Andrew Lamb, Susan Tu, Andres Nötzli, Kunle Olukotun, and Christopher Ré. 2017. Emptyheaded: A relational engine for graph processing. ACM Transactions on Database Systems (TODS), 42(4):1–44. [find](https://scholar.google.com/scholar?q=Christopher+R+Aberger%2C+Andrew+Lamb%2C+Susan+Tu%2C+Andres+N%C3%B6tzli%2C+Kunle+Olukotun%2C+and+Christopher+R%C3%A9%2E+2017%2E+Emptyheaded%3A+A+relational+engine+for+graph+processing%2E+ACM+Transactions+on+Database+Systems+%28TODS)
2. Khaled Ammar, Frank McSherry, Semih Salihoglu, and Manas Joglekar. 2018. Distributed evaluation of subgraph queries using worstcase optimal lowmemory dataflows. arXiv preprint arXiv:1802.03760. — [arXiv:1802.03760](https://arxiv.org/abs/1802.03760) [find](https://scholar.google.com/scholar?q=Khaled+Ammar%2C+Frank+McSherry%2C+Semih+Salihoglu%2C+and+Manas+Joglekar%2E+2018%2E+Distributed+evaluation+of+subgraph+queries+using+worstcase+optimal+lowmemory+dataflows%2E+arXiv+preprint+arXiv%3A1802%2E03760%2E+%E2%80%94+%5BarX)
3. Kohei Arai. 2024. Design of on-premises version of rag with ai agent for framework selection together with dify and dsl as well as ollama for llm. International Journal of Advanced Computer Science & Applications, 15(12). [find](https://scholar.google.com/scholar?q=Kohei+Arai%2E+2024%2E+Design+of+on%2Dpremises+version+of+rag+with+ai+agent+for+framework+selection+together+with+dify+and+dsl+as+well+as+ollama+for+llm%2E+International+Journal+of+Advanced+Computer+Science+%26+)
4. Bibek Bhattarai, Hang Liu, and H Howie Huang. 2019. Ceci: Compact embedding cluster index for scalable subgraph matching. In Proceedings of the 2019 International Conference on Management of Data, pages 1447–1462. [find](https://scholar.google.com/scholar?q=Bibek+Bhattarai%2C+Hang+Liu%2C+and+H+Howie+Huang%2E+2019%2E+Ceci%3A+Compact+embedding+cluster+index+for+scalable+subgraph+matching%2E+In+Proceedings+of+the+2019+International+Conference+on+Management+of+Data%2C+pag)
5. Fei Bi, Lijun Chang, Xuemin Lin, Lu Qin, and Wenjie Zhang. 2016. Efficient subgraph matching by postponing cartesian products. In Proceedings of the 2016 International Conference on Management of Data, pages 1199–1214. [find](https://scholar.google.com/scholar?q=Fei+Bi%2C+Lijun+Chang%2C+Xuemin+Lin%2C+Lu+Qin%2C+and+Wenjie+Zhang%2E+2016%2E+Efficient+subgraph+matching+by+postponing+cartesian+products%2E+In+Proceedings+of+the+2016+International+Conference+on+Management+of+Data)
6. Vincenzo Bonnici, Rosalba Giugno, Alfredo Pulvirenti, Dennis Shasha, and Alfredo Ferro. 2013. A subgraph isomorphism algorithm and its application to biochemical data. BMC bioinformatics, 14(Suppl 7):S13. [find](https://scholar.google.com/scholar?q=Vincenzo+Bonnici%2C+Rosalba+Giugno%2C+Alfredo+Pulvirenti%2C+Dennis+Shasha%2C+and+Alfredo+Ferro%2E+2013%2E+A+subgraph+isomorphism+algorithm+and+its+application+to+biochemical+data%2E+BMC+bioinformatics%2C+14%28Suppl+7%29%3A)
7. Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+approach+to+query%2Dfocused+summarization%2E+arXiv+preprint+arXiv%3A2404%2E16130%2E)
8. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2023. [Precise zero-shot dense retrieval without relevance labels](https://md.research.elamur.ai/free/en/papers/gao-2022-precise-zero-shot-dense-retrieval/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1762–1777.
9. Xinbo Gao, Bing Xiao, Dacheng Tao, and Xuelong Li. 2010. A survey of graph edit distance. Pattern Analysis and applications, 13(1):113–129. [find](https://scholar.google.com/scholar?q=Xinbo+Gao%2C+Bing+Xiao%2C+Dacheng+Tao%2C+and+Xuelong+Li%2E+2010%2E+A+survey+of+graph+edit+distance%2E+Pattern+Analysis+and+applications%2C+13%281%29%3A113%E2%80%93129%2E)
10. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2024. [Lightrag: Simple and fast retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/guo-2024-lightrag-simple-fast-retrieval-augmented/). arXiv preprint arXiv:2410.05779.
11. Wook-Shin Han, Jinsoo Lee, and Jeong-Hoon Lee. 2013. Turboiso: towards ultrafast and robust subgraph isomorphism search in large graph databases. In Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, SIGMOD ’13, page 337–348, New York, NY, USA. Association for Computi… [find](https://scholar.google.com/scholar?q=Wook%2DShin+Han%2C+Jinsoo+Lee%2C+and+Jeong%2DHoon+Lee%2E+2013%2E+Turboiso%3A+towards+ultrafast+and+robust+subgraph+isomorphism+search+in+large+graph+databases%2E+In+Proceedings+of+the+2013+ACM+SIGMOD+International+Co)
12. Huahai He and Ambuj K Singh. 2008. Graphs-at-a-time: query language and access methods for graph databases. In Proceedings of the 2008 ACM SIG-MOD international conference on Management of data, pages 405–418. [find](https://scholar.google.com/scholar?q=Huahai+He+and+Ambuj+K+Singh%2E+2008%2E+Graphs%2Dat%2Da%2Dtime%3A+query+language+and+access+methods+for+graph+databases%2E+In+Proceedings+of+the+2008+ACM+SIG%2DMOD+international+conference+on+Management+of+data%2C+pages)
13. Vincenzo Carletti, Pasquale Foggia, Alessia Saggese, and Mario Vento. 2017. Challenging the time complexity of exact subgraph isomorphism for huge and dense graphs with vf3. IEEE transactions on pattern analysis and machine intelligence, 40(4):804–818. [find](https://scholar.google.com/scholar?q=Vincenzo+Carletti%2C+Pasquale+Foggia%2C+Alessia+Saggese%2C+and+Mario+Vento%2E+2017%2E+Challenging+the+time+complexity+of+exact+subgraph+isomorphism+for+huge+and+dense+graphs+with+vf3%2E+IEEE+transactions+on+patte)
14. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2025. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems,…
15. Vincenzo Carletti, Pasquale Foggia, and Mario Vento. 2015. Vf2 plus: An improved version of vf2 for biological graphs. In International Workshop on Graph-Based Representations in Pattern Recognition, pages 168–177. Springer. [find](https://scholar.google.com/scholar?q=Vincenzo+Carletti%2C+Pasquale+Foggia%2C+and+Mario+Vento%2E+2015%2E+Vf2+plus%3A+An+improved+version+of+vf2+for+biological+graphs%2E+In+International+Workshop+on+Graph%2DBased+Representations+in+Pattern+Recognition%2C+)
16. Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. [Hipporag: Neurobiologically inspired long-term memory for large language models](https://md.research.elamur.ai/free/en/papers/gutierrez-2024-hipporag-neurobiologically-inspired-long-term/). Advances in Neural Information Processing Systems, 37:59532–59569.
17. Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, and Jie Fu. 2024. [Rq-rag: Learning to refine queries for retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/chan-2024-rq-rag-learning-refine-queries/). arXiv preprint arXiv:2404.00610.
18. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, and 1 others. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Lin…
19. Shawn Curran, Sam Lansley, and Oliver Bethell. 2023. Hallucination is the last thing you need. arXiv preprint arXiv:2306.11520. — [arXiv:2306.11520](https://arxiv.org/abs/2306.11520) [find](https://scholar.google.com/scholar?q=Shawn+Curran%2C+Sam+Lansley%2C+and+Oliver+Bethell%2E+2023%2E+Hallucination+is+the+last+thing+you+need%2E+arXiv+preprint+arXiv%3A2306%2E11520%2E+%E2%80%94+%5BarXiv%3A2306%2E11520%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2306%2E11520%29)
20. Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2024. [The faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/). arXiv preprint arXiv:2401.08281.
21. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Longbin Lai, Lu Qin, Xuemin Lin, and Lijun Chang. 2015. Scalable subgraph enumeration in mapreduce. Proceedings of the VLDB Endowment, 8(10):2150– 8097. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Longbin+Lai%2C+Lu+Qin%2C+Xuemin+Lin%2C+and+Lijun+Chang%2E+2015%2E+Scalable+subgraph+enumeration+in+mapreduce%2E+Proceedi)
22. Longbin Lai, Lu Qin, Xuemin Lin, Ying Zhang, Lijun Chang, and Shiyu Yang. 2016. Scalable distributed subgraph enumeration. Proceedings of the VLDB Endowment, 10(3):217–228. [find](https://scholar.google.com/scholar?q=Longbin+Lai%2C+Lu+Qin%2C+Xuemin+Lin%2C+Ying+Zhang%2C+Lijun+Chang%2C+and+Shiyu+Yang%2E+2016%2E+Scalable+distributed+subgraph+enumeration%2E+Proceedings+of+the+VLDB+Endowment%2C+10%283%29%3A217%E2%80%93228%2E)
23. Longbin Lai, Zhu Qing, Zhengyi Yang, Xin Jin, Zheng-min Lai, Ran Wang, Kongzhang Hao, Xuemin Lin, Lu Qin, Wenjie Zhang, and 1 others. 2019. Distributed subgraph matching on timely dataflow. Proceedings of the VLDB Endowment, 12(10):1099– 1112. [find](https://scholar.google.com/scholar?q=Longbin+Lai%2C+Zhu+Qing%2C+Zhengyi+Yang%2C+Xin+Jin%2C+Zheng%2Dmin+Lai%2C+Ran+Wang%2C+Kongzhang+Hao%2C+Xuemin+Lin%2C+Lu+Qin%2C+Wenjie+Zhang%2C+and+1+others%2E+2019%2E+Distributed+subgraph+matching+on+timely+dataflow%2E+Proceeding)
24. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
25. Mufei Li, Siqi Miao, and Pan Li. 2025a. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. Preprint, arXiv:2410.20724. — [arXiv:2410.20724](https://arxiv.org/abs/2410.20724) [find](https://scholar.google.com/scholar?q=Mufei+Li%2C+Siqi+Miao%2C+and+Pan+Li%2E+2025a%2E+Simple+is+effective%3A+The+roles+of+graphs+and+large+language+models+in+knowledge%2Dgraph%2Dbased+retrieval%2Daugmented+generation%2E+Preprint%2C+arXiv%3A2410%2E20724%2E+%E2%80%94+%5BarXiv)
26. Yuhan Li, Xinni Zhang, Linhao Luo, Heng Chang, Yuxiang Ren, Irwin King, and Jia Li. 2025b. G-refer: Graph retrieval-augmented large language model for explainable recommendation. In Proceedings of the ACM on Web Conference 2025, pages 240–251. [find](https://scholar.google.com/scholar?q=Yuhan+Li%2C+Xinni+Zhang%2C+Linhao+Luo%2C+Heng+Chang%2C+Yuxiang+Ren%2C+Irwin+King%2C+and+Jia+Li%2E+2025b%2E+G%2Drefer%3A+Graph+retrieval%2Daugmented+large+language+model+for+explainable+recommendation%2E+In+Proceedings+of+the)
27. Lei Liang, Zhongpu Bo, Zhengke Gui, Zhongshu Zhu, Ling Zhong, Peilong Zhao, Mengshu Sun, Zhiqiang Zhang, Jun Zhou, Wenguang Chen, Wen Zhang, and Huajun Chen. 2025. Kag: Boosting llms in professional domains via knowledge augmented generation. In Companion Proceedings of the ACM on Web Conference 202… [find](https://scholar.google.com/scholar?q=Lei+Liang%2C+Zhongpu+Bo%2C+Zhengke+Gui%2C+Zhongshu+Zhu%2C+Ling+Zhong%2C+Peilong+Zhao%2C+Mengshu+Sun%2C+Zhiqiang+Zhang%2C+Jun+Zhou%2C+Wenguang+Chen%2C+Wen+Zhang%2C+and+Huajun+Chen%2E+2025%2E+Kag%3A+Boosting+llms+in+professional+d)
28. Hao Liu, Zhengren Wang, Xi Chen, Zhiyu Li, Feiyu Xiong, Qinhan Yu, and Wentao Zhang. 2025. Hoprag: Multi-hop reasoning for logic-aware retrieval-augmented generation. arXiv preprint arXiv:2502.12442. [find](https://scholar.google.com/scholar?q=Hao+Liu%2C+Zhengren+Wang%2C+Xi+Chen%2C+Zhiyu+Li%2C+Feiyu+Xiong%2C+Qinhan+Yu%2C+and+Wentao+Zhang%2E+2025%2E+Hoprag%3A+Multi%2Dhop+reasoning+for+logic%2Daware+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2502%2E12442%2E)
29. Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, and Luu Anh Tuan. 2025. Hypergraphrag: Retrieval-augmented generation via hypergraph-structured knowledge representation. Preprint, arXiv:2503.21322. — [arXiv:2503.21322](https://arxiv.org/abs/2503.21322) [find](https://scholar.google.com/scholar?q=Haoran+Luo%2C+Haihong+E%2C+Guanting+Chen%2C+Yandan+Zheng%2C+Xiaobao+Wu%2C+Yikai+Guo%2C+Qika+Lin%2C+Yu+Feng%2C+Zemin+Kuang%2C+Meina+Song%2C+Yifan+Zhu%2C+and+Luu+Anh+Tuan%2E+2025%2E+Hypergraphrag%3A+Retrieval%2Daugmented+generation+)
30. Junliang Luo, Tianyu Li, Di Wu, Michael Jenkin, Steve Liu, and Gregory Dudek. 2024. Hallucination detection and hallucination mitigation: An investigation. arXiv preprint arXiv:2401.08358. — [arXiv:2401.08358](https://arxiv.org/abs/2401.08358) [find](https://scholar.google.com/scholar?q=Junliang+Luo%2C+Tianyu+Li%2C+Di+Wu%2C+Michael+Jenkin%2C+Steve+Liu%2C+and+Gregory+Dudek%2E+2024%2E+Hallucination+detection+and+hallucination+mitigation%3A+An+investigation%2E+arXiv+preprint+arXiv%3A2401%2E08358%2E+%E2%80%94+%5BarXiv%3A24)
31. Amine Mhedhbi and Semih Salihoglu. 2019. Optimizing subgraph queries by combining binary and worst-case optimal joins. arXiv preprint arXiv:1903.02076. — [arXiv:1903.02076](https://arxiv.org/abs/1903.02076) [find](https://scholar.google.com/scholar?q=Amine+Mhedhbi+and+Semih+Salihoglu%2E+2019%2E+Optimizing+subgraph+queries+by+combining+binary+and+worst%2Dcase+optimal+joins%2E+arXiv+preprint+arXiv%3A1903%2E02076%2E+%E2%80%94+%5BarXiv%3A1903%2E02076%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1903%2E)
32. Hongjin Qian, Peitian Zhang, Zheng Liu, Kelong Mao, and Zhicheng Dou. 2024. Memorag: Moving towards next-gen rag via memory-inspired knowledge discovery. arXiv preprint arXiv:2409.05591, 1. — [arXiv:2409.05591](https://arxiv.org/abs/2409.05591) [find](https://scholar.google.com/scholar?q=Hongjin+Qian%2C+Peitian+Zhang%2C+Zheng+Liu%2C+Kelong+Mao%2C+and+Zhicheng+Dou%2E+2024%2E+Memorag%3A+Moving+towards+next%2Dgen+rag+via+memory%2Dinspired+knowledge+discovery%2E+arXiv+preprint+arXiv%3A2409%2E05591%2C+1%2E+%E2%80%94+%5BarXiv%3A2)
33. Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D Manning. 2024. [Raptor: Recursive abstractive processing for tree-organized retrieval](https://md.research.elamur.ai/free/en/papers/sarthi-2024-raptor-recursive-abstractive-processing-tree/). In The Twelfth International Conference on Learning Representations.
34. Haichuan Shang, Ying Zhang, Xuemin Lin, and Jeffrey Xu Yu. 2008. Taming verification hardness: an efficient algorithm for testing subgraph isomorphism. Proceedings of the VLDB Endowment, 1(1):364–375. [find](https://scholar.google.com/scholar?q=Haichuan+Shang%2C+Ying+Zhang%2C+Xuemin+Lin%2C+and+Jeffrey+Xu+Yu%2E+2008%2E+Taming+verification+hardness%3A+an+efficient+algorithm+for+testing+subgraph+isomorphism%2E+Proceedings+of+the+VLDB+Endowment%2C+1%281%29%3A364%E2%80%93375%2E)
35. Peiqi Sui, Eamon Duede, Sophie Wu, and Richard Jean So. 2024. Confabulation: The surprising value of large language model hallucinations. arXiv preprint arXiv:2406.04175. [find](https://scholar.google.com/scholar?q=Peiqi+Sui%2C+Eamon+Duede%2C+Sophie+Wu%2C+and+Richard+Jean+So%2E+2024%2E+Confabulation%3A+The+surprising+value+of+large+language+model+hallucinations%2E+arXiv+preprint+arXiv%3A2406%2E04175%2E)
36. Shixuan Sun, Xibo Sun, Yulin Che, Qiong Luo, and Bingsheng He. 2020. Rapidmatch: A holistic approach to subgraph query processing. Proceedings of the VLDB Endowment, 14(2):176–188. [find](https://scholar.google.com/scholar?q=Shixuan+Sun%2C+Xibo+Sun%2C+Yulin+Che%2C+Qiong+Luo%2C+and+Bingsheng+He%2E+2020%2E+Rapidmatch%3A+A+holistic+approach+to+subgraph+query+processing%2E+Proceedings+of+the+VLDB+Endowment%2C+14%282%29%3A176%E2%80%93188%2E)
37. Zhao Sun, Hongzhi Wang, Haixun Wang, Bin Shao, and Jianzhong Li. 2012. Efficient subgraph matching on billion node graphs. arXiv preprint arXiv:1205.6691. — [arXiv:1205.6691](https://arxiv.org/abs/1205.6691) [find](https://scholar.google.com/scholar?q=Zhao+Sun%2C+Hongzhi+Wang%2C+Haixun+Wang%2C+Bin+Shao%2C+and+Jianzhong+Li%2E+2012%2E+Efficient+subgraph+matching+on+billion+node+graphs%2E+arXiv+preprint+arXiv%3A1205%2E6691%2E+%E2%80%94+%5BarXiv%3A1205%2E6691%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F120)
38. Yuqiao Tan, Shizhu He, Huanxuan Liao, Jun Zhao, and Kang Liu. 2025. Dynamic parametric retrieval augmented generation for test-time knowledge enhancement. Preprint, arXiv:2503.23895. — [arXiv:2503.23895](https://arxiv.org/abs/2503.23895) [find](https://scholar.google.com/scholar?q=Yuqiao+Tan%2C+Shizhu+He%2C+Huanxuan+Liao%2C+Jun+Zhao%2C+and+Kang+Liu%2E+2025%2E+Dynamic+parametric+retrieval+augmented+generation+for+test%2Dtime+knowledge+enhancement%2E+Preprint%2C+arXiv%3A2503%2E23895%2E+%E2%80%94+%5BarXiv%3A2503%2E238)
39. Oguzhan Topsakal and Tahir Cetin Akinci. 2023. Creating large language model applications utilizing langchain: A primer on developing llm apps fast. In International conference on applied engineering and natural sciences, volume 1, pages 1050–1056. [find](https://scholar.google.com/scholar?q=Oguzhan+Topsakal+and+Tahir+Cetin+Akinci%2E+2023%2E+Creating+large+language+model+applications+utilizing+langchain%3A+A+primer+on+developing+llm+apps+fast%2E+In+International+conference+on+applied+engineering+)
40. Chaohui Wang, Miao Xie, Sourav S. Bhowmick, Byron Choi, Xiaokui Xiao, and Shuigeng Zhou. 2019. An indexing framework for efficient visual exploratory subgraph search in graph databases. In 2019 IEEE 35th International Conference on Data Engineering (ICDE), pages 1666–1669. [find](https://scholar.google.com/scholar?q=Chaohui+Wang%2C+Miao+Xie%2C+Sourav+S%2E+Bhowmick%2C+Byron+Choi%2C+Xiaokui+Xiao%2C+and+Shuigeng+Zhou%2E+2019%2E+An+indexing+framework+for+efficient+visual+exploratory+subgraph+search+in+graph+databases%2E+In+2019+IEEE+3)
41. Chaohui Wang, Miao Xie, Sourav S Bhowmick, Byron Choi, Xiaokui Xiao, and Shuigeng Zhou. 2020. Ferrari: an efficient framework for visual exploratory subgraph search in graph databases. The VLDB Journal, 29(5):973–998. [find](https://scholar.google.com/scholar?q=Chaohui+Wang%2C+Miao+Xie%2C+Sourav+S+Bhowmick%2C+Byron+Choi%2C+Xiaokui+Xiao%2C+and+Shuigeng+Zhou%2E+2020%2E+Ferrari%3A+an+efficient+framework+for+visual+exploratory+subgraph+search+in+graph+databases%2E+The+VLDB+Journa)
42. Hung Q Ngo, Ely Porat, Christopher Ré, and Atri Rudra. 2018. Worst-case optimal join algorithms. Journal of the ACM (JACM), 65(3):1–40. [find](https://scholar.google.com/scholar?q=Hung+Q+Ngo%2C+Ely+Porat%2C+Christopher+R%C3%A9%2C+and+Atri+Rudra%2E+2018%2E+Worst%2Dcase+optimal+join+algorithms%2E+Journal+of+the+ACM+%28JACM%29%2C+65%283%29%3A1%E2%80%9340%2E)
43. Miao Xie, Sourav S Bhowmick, Gao Cong, and Qing Wang. 2017. Panda: toward partial topology-based search on large networks in a single machine. The VLDB Journal, 26(2):203–228. [find](https://scholar.google.com/scholar?q=Miao+Xie%2C+Sourav+S+Bhowmick%2C+Gao+Cong%2C+and+Qing+Wang%2E+2017%2E+Panda%3A+toward+partial+topology%2Dbased+search+on+large+networks+in+a+single+machine%2E+The+VLDB+Journal%2C+26%282%29%3A203%E2%80%93228%2E)
44. A Pal, LK Umapathi, and M Sankarasubbu. 2023. [Med-halt: medical domain hallucination test for large language models](https://md.research.elamur.ai/free/en/papers/pal-2023-med-halt-medical-domain-hallucination/). arxiv. arXiv preprint arXiv:2307.15343.
45. Miao Xie, Sourav S Bhowmick, Hao Su, Gao Cong, and Wook-Shin Han. 2018. Panda: a system for partial topology-based search on large networks. Proc. VLDB Endow., 11(12):1966–1969. [find](https://scholar.google.com/scholar?q=Miao+Xie%2C+Sourav+S+Bhowmick%2C+Hao+Su%2C+Gao+Cong%2C+and+Wook%2DShin+Han%2E+2018%2E+Panda%3A+a+system+for+partial+topology%2Dbased+search+on+large+networks%2E+Proc%2E+VLDB+Endow%2E%2C+11%2812%29%3A1966%E2%80%931969%2E)
46. Derong Xu, Pengyue Jia, Xiaopeng Li, Yingyi Zhang, Maolin Wang, Qidong Liu, Xiangyu Zhao, Yichao Wang, Huifeng Guo, Ruiming Tang, and 1 others. 2025a. Align-grag: Reasoning-guided dual alignment for graph retrieval-augmented generation. arXiv preprint arXiv:2505.16237. — [arXiv:2505.16237](https://arxiv.org/abs/2505.16237) [find](https://scholar.google.com/scholar?q=Derong+Xu%2C+Pengyue+Jia%2C+Xiaopeng+Li%2C+Yingyi+Zhang%2C+Maolin+Wang%2C+Qidong+Liu%2C+Xiangyu+Zhao%2C+Yichao+Wang%2C+Huifeng+Guo%2C+Ruiming+Tang%2C+and+1+others%2E+2025a%2E+Align%2Dgrag%3A+Reasoning%2Dguided+dual+alignment+for+g)
47. Derong Xu, Xinhang Li, Ziheng Zhang, Zhenxi Lin, Zhihong Zhu, Zhi Zheng, Xian Wu, Xiangyu Zhao, Tong Xu, and Enhong Chen. 2025b. Harnessing large language models for knowledge graph question answering via adaptive multi-aspect retrieval-augmentation. In Proceedings of the AAAI Conference on Artifici… [find](https://scholar.google.com/scholar?q=Derong+Xu%2C+Xinhang+Li%2C+Ziheng+Zhang%2C+Zhenxi+Lin%2C+Zhihong+Zhu%2C+Zhi+Zheng%2C+Xian+Wu%2C+Xiangyu+Zhao%2C+Tong+Xu%2C+and+Enhong+Chen%2E+2025b%2E+Harnessing+large+language+models+for+knowledge+graph+question+answering)
48. Yutong Ye, Xiang Lian, and Mingsong Chen. 2024. Efficient exact subgraph matching via gnn-based path dominance embedding. Proceedings of the VLDB Endowment, 17(7):1628–1641. [find](https://scholar.google.com/scholar?q=Yutong+Ye%2C+Xiang+Lian%2C+and+Mingsong+Chen%2E+2024%2E+Efficient+exact+subgraph+matching+via+gnn%2Dbased+path+dominance+embedding%2E+Proceedings+of+the+VLDB+Endowment%2C+17%287%29%3A1628%E2%80%931641%2E)
49. Ziheng Zhang, Zhenxi Lin, Yefeng Zheng, and Xian Wu. 2025. How much medical knowledge do llms have? an evaluation of medical knowledge coverage for llms. In Proceedings of the ACM on Web Conference 2025, pages 5330–5341. [find](https://scholar.google.com/scholar?q=Ziheng+Zhang%2C+Zhenxi+Lin%2C+Yefeng+Zheng%2C+and+Xian+Wu%2E+2025%2E+How+much+medical+knowledge+do+llms+have%3F+an+evaluation+of+medical+knowledge+coverage+for+llms%2E+In+Proceedings+of+the+ACM+on+Web+Conference+20)
50. Xuejiao Zhao, Siyan Liu, Su-Yin Yang, and Chunyan Miao. 2025. Medrag: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot. In Proceedings of the ACM on Web Conference 2025, pages 4442–4457. [find](https://scholar.google.com/scholar?q=Xuejiao+Zhao%2C+Siyan+Liu%2C+Su%2DYin+Yang%2C+and+Chunyan+Miao%2E+2025%2E+Medrag%3A+Enhancing+retrieval%2Daugmented+generation+with+knowledge+graph%2Delicited+reasoning+for+healthcare+copilot%2E+In+Proceedings+of+the+ACM)
51. Luyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, and Xiao Huang. 2025. Linearrag: Linear graph retrieval augmented generation on large-scale corpora. Preprint, arXiv:2510.10114. — [arXiv:2510.10114](https://arxiv.org/abs/2510.10114) [find](https://scholar.google.com/scholar?q=Luyao+Zhuang%2C+Shengyuan+Chen%2C+Yilin+Xiao%2C+Huachi+Zhou%2C+Yujing+Zhang%2C+Hao+Chen%2C+Qinggang+Zhang%2C+and+Xiao+Huang%2E+2025%2E+Linearrag%3A+Linear+graph+retrieval+augmented+generation+on+large%2Dscale+corpora%2E+Prep)

*Updated 2 November 2026*