---
title: "Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic"
description: "They propose a schema-agnostic framework that automatically builds synthetic evaluation sets from any knowledge graph. 41 references."
authors: ["Thibaud Vanmechelen", "Alexandre Achten", "Zaineb Gabsi", "Sabri Skhiri"]
year: 2026
venue: "Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26"
source: "https://aclanthology.org/2026.kallm-1.18/"
doi: "10.63317/5h4oct2t73a2"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/vanmechelen-2026-quantifying-retrieval-quality-graphrag-schema/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vanmechelen-2026-quantifying-retrieval-quality-graphrag-schema/)

[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/40/) / Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach

# Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach

**Authors:** Thibaud Vanmechelen, Alexandre Achten, Zaineb Gabsi and Sabri Skhiri · **Year:** 2026 · **Venue:** [Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26](https://md.research.elamur.ai/free/en/venues/kallm/) ([Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26 2026](https://md.research.elamur.ai/free/en/venues/kallm/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.kallm-1.18/) · [PDF](https://aclanthology.org/2026.kallm-1.18.pdf) · [DOI 10.63317/5h4oct2t73a2](https://doi.org/10.63317/5h4oct2t73a2) · [OpenAlex](https://openalex.org/W7166521851)

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

## Summary
Evaluations of GraphRAG systems usually score only the final LLM answer, so they cannot tell whether a mistake comes from missing graph evidence or from the generator. The authors target the retrieval step itself. They propose a schema-agnostic framework that automatically builds synthetic evaluation sets from any knowledge graph. It instantiates parameterised Cypher query templates, which yields deterministic, exactly verifiable ground-truth subgraphs. The questions cover nine categories, ranging from simple lookups to multi-hop, aggregation, negation, intersection and out-of-scope cases. As a case study, they generate a benchmark from a filtered biochemical subset of Hetionet hosted in Neo4j and test four retrieval architectures of different kinds. Agentic, LLM-driven retrievers achieved the best recall and coped best with complex graph topology, while the other approaches struggled. The work matters because it replaces semantic-similarity proxies with structurally precise, reproducible measurement. This supports systematic tracking of retriever quality in graph-based RAG pipelines.

## Key points
- The source KG is a Hetionet subset containing 10 relation types and 5 kinds of nodes: pathways, biological processes, molecular functions, compounds and genes. It has 38,584 nodes and 1,488,879 edges, deployed in Neo4j.
- The graph is mostly structural, with nodes carrying few attributes, so answers depend on topology rather than text.
- Ground truth comes from Cypher templates grouped into nine query categories. Examples include aggregation counts, missing-edge (negative) checks, two-source intersections, and general or domain-specific out-of-scope questions.
- The framework extends earlier qualitative work by Houimli et al. (2025), which relied on ARES and a fine-tuned BioBERT. The new framework adds quantitative, correctness-guaranteed evaluation.
- Four retrieval approaches were compared, and agentic LLM-based retrieval gave the highest recall and reasoning capacity.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Thibaud Vanmechelen, Alexandre Achten, Zaineb Gabsi and Sabri Skhiri. 2026. Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach. Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{vanmechelen2026quantifying,
  title = {{Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach}},
  author = {Thibaud Vanmechelen, Alexandre Achten, Zaineb Gabsi and Sabri Skhiri},
  booktitle = {Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26},
  year = {2026},
  doi = {10.63317/5h4oct2t73a2},
  url = {https://doi.org/10.63317/5h4oct2t73a2}
}
```

- [← previous Quantifying Metric and Model Agreement in Bias Evaluation of Large Language Models](https://md.research.elamur.ai/free/en/papers/asgari-2026-quantifying-metric-model-agreement-bias/)
- [next → Quantifying Social Sentiment in Hostels Using A Domain-Specific Transformer Pipeline](https://md.research.elamur.ai/free/en/papers/mcmurry-2026-quantifying-social-sentiment-hostels-domain/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/)

## References

41 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ali Ahmadi, Iman Gholami, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, and Mohammad Mahdavi. 2024. Prize-collecting steiner tree: A 1.79 approximation. In Proceedings of the 56th Annual ACM Symposium on Theory of Computing, pages 1641–1652. [find](https://scholar.google.com/scholar?q=Ali+Ahmadi%2C+Iman+Gholami%2C+MohammadTaghi+Hajiaghayi%2C+Peyman+Jabbarzade%2C+and+Mohammad+Mahdavi%2E+2024%2E+Prize%2Dcollecting+steiner+tree%3A+A+1%2E79+approximation%2E+In+Proceedings+of+the+56th+Annual+ACM+Symposium+)
2. Joyce Cahoon, Prerna Singh, Nick Litombe, Jonathan Larson, Ha Trinh, Yiwen Zhu, Andreas Mueller, Fotis Psallidas, and Carlo Curino. 2025. Optimizing open-domain question answering with graph-based retrieval augmented generation. In Proceedings of the 1st workshop connecting academia and industry on… [find](https://scholar.google.com/scholar?q=Joyce+Cahoon%2C+Prerna+Singh%2C+Nick+Litombe%2C+Jonathan+Larson%2C+Ha+Trinh%2C+Yiwen+Zhu%2C+Andreas+Mueller%2C+Fotis+Psallidas%2C+and+Carlo+Curino%2E+2025%2E+Optimizing+open%2Ddomain+question+answering+with+graph%2Dbased+ret)
3. Haoting Chen, Sergio José Rodríguez Méndez, and Pouya Ghiasnezhad Omran. 2025. Open local knowledge graph construction from academic papers using generative large language models. In Companion Proceedings of the ACM on Web Conference 2025, pages 2551–2559. [find](https://scholar.google.com/scholar?q=Haoting+Chen%2C+Sergio+Jos%C3%A9+Rodr%C3%ADguez+M%C3%A9ndez%2C+and+Pouya+Ghiasnezhad+Omran%2E+2025%2E+Open+local+knowledge+graph+construction+from+academic+papers+using+generative+large+language+models%2E+In+Companion+Proceed)
4. Seungmin Choi and Yuchul Jung. 2025. Knowledge graph construction: Extraction, learning, and evaluation. Applied Sciences, 15(7):3727. [find](https://scholar.google.com/scholar?q=Seungmin+Choi+and+Yuchul+Jung%2E+2025%2E+Knowledge+graph+construction%3A+Extraction%2C+learning%2C+and+evaluation%2E+Applied+Sciences%2C+15%287%29%3A3727%2E)
5. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, 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=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+app)
6. Shahul Es, Jithin James, Luis Espinosa Anke, and Steven Schockaert. 2024. [Ragas: Automated evaluation of retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/es-2023-ragas-automated-evaluation-retrieval-augmented/). In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 150–158.
7. Yanlin Feng, Xinyue Chen, Bill Yuchen Lin, Peifeng Wang, Jun Yan, and Xiang Ren. 2020. [Scalable multi-hop relational reasoning for knowledge-aware question answering](https://md.research.elamur.ai/free/en/papers/feng-2020-scalable-multi-hop-relational-reasoning/). arXiv preprint arXiv:2005.00646.
8. Robert Friel, Masha Belyi, and Atindriyo Sanyal. 2024. Ragbench: Explainable benchmark for retrieval-augmented generation systems. arXiv preprint arXiv:2407.11005. — [arXiv:2407.11005](https://arxiv.org/abs/2407.11005) [find](https://scholar.google.com/scholar?q=Robert+Friel%2C+Masha+Belyi%2C+and+Atindriyo+Sanyal%2E+2024%2E+Ragbench%3A+Explainable+benchmark+for+retrieval%2Daugmented+generation+systems%2E+arXiv+preprint+arXiv%3A2407%2E11005%2E+%E2%80%94+%5BarXiv%3A2407%2E11005%5D%28https%3A%2F%2Farxiv%2Eo)
9. Yifu Gao, Linbo Qiao, Zhigang Kan, Zhihua Wen, Yongquan He, and Dongsheng Li. 2024. Two-stage generative question answering on temporal knowledge graph using large language models. arXiv preprint arXiv:2402.16568. [find](https://scholar.google.com/scholar?q=Yifu+Gao%2C+Linbo+Qiao%2C+Zhigang+Kan%2C+Zhihua+Wen%2C+Yongquan+He%2C+and+Dongsheng+Li%2E+2024%2E+Two%2Dstage+generative+question+answering+on+temporal+knowledge+graph+using+large+language+models%2E+arXiv+preprint+arXi)
10. Tingfeng Guo, Qihui Yang, Chao Wang, Yulu Liu, Peng Li, Jian Tang, and Yuzhuo Wen. 2024. Knowledgenavigator: leveraging large language models for enhanced reasoning over knowledge graph. Complex & Intelligent Systems, 10(5):7063–7076. [find](https://scholar.google.com/scholar?q=Tingfeng+Guo%2C+Qihui+Yang%2C+Chao+Wang%2C+Yulu+Liu%2C+Peng+Li%2C+Jian+Tang%2C+and+Yuzhuo+Wen%2E+2024%2E+Knowledgenavigator%3A+leveraging+large+language+models+for+enhanced+reasoning+over+knowledge+graph%2E+Complex+%26+Int)
11. Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. [Inductive representation learning on large graphs](https://md.research.elamur.ai/free/en/papers/hamilton-2017-inductive-representation-learning-large-graphs/). Advances in neural information processing systems, 30.
12. Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A Rossi, Subhabrata Mukherjee, Xianfeng Tang, et al. 2024. [Retrieval augmented generation with graphs (graphrag)](https://md.research.elamur.ai/free/en/papers/es-2023-ragas-automated-evaluation-retrieval-augmented/). arXiv preprint arXiv:2309.15217.
13. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. [G-retriever: Retrieval-augmented generation for textual graph understanding and question answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/). Advances in Neural Information Processing Systems, 37:132876–132907.
14. Daniel Himmelstein, Antoine Lizee, Faisal Alquad-doomi, Vincent Rubinetti, Dongbo Hu, Casey Greene, and Sergio Baranzini. 2016. het-io/hetionet: Data repository containing Hetionet downloads. [find](https://scholar.google.com/scholar?q=Daniel+Himmelstein%2C+Antoine+Lizee%2C+Faisal+Alquad%2Ddoomi%2C+Vincent+Rubinetti%2C+Dongbo+Hu%2C+Casey+Greene%2C+and+Sergio+Baranzini%2E+2016%2E+het%2Dio%2Fhetionet%3A+Data+repository+containing+Hetionet+downloads%2E)
15. Asma Houimli, Zaineb Gabsi, and Sabri Skhiri. 2025. Evaluation of graphrag strategies for efficient information retrieval. [find](https://scholar.google.com/scholar?q=Asma+Houimli%2C+Zaineb+Gabsi%2C+and+Sabri+Skhiri%2E+2025%2E+Evaluation+of+graphrag+strategies+for+efficient+information+retrieval%2E)
16. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 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, 43(2):…
17. Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Structgpt: A general framework for large language model to reason over structured data. arXiv preprint arXiv:2305.09645. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Zican+Dong%2C+Keming+Ye%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023%2E+Structgpt%3A+A+general+framework+for+large+language+model+to+reason+over+structured+data%2E+arXiv+preprint+arXiv%3A2305%2E)
18. Jiho Kim, Yeonsu Kwon, Yohan Jo, and Edward Choi. 2023. Kg-gpt: A general framework for reasoning on knowledge graphs using large language models. arXiv preprint arXiv:2310.11220. [find](https://scholar.google.com/scholar?q=Jiho+Kim%2C+Yeonsu+Kwon%2C+Yohan+Jo%2C+and+Edward+Choi%2E+2023%2E+Kg%2Dgpt%3A+A+general+framework+for+reasoning+on+knowledge+graphs+using+large+language+models%2E+arXiv+preprint+arXiv%3A2310%2E11220%2E)
19. Jinhyuk Lee, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, and Jaewoo Kang. 2020. [Biobert: a pre-trained biomedical language representation model for biomedical text mining](https://md.research.elamur.ai/free/en/papers/lee-2019-biobert-pre-trained-biomedical-language/). Bioinformatics, 36(4):1234–1240.
20. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 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, 33:9459–9474.
21. Chin-Yew Lin and Franz Josef Och. 2004. [Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics](https://md.research.elamur.ai/free/en/papers/lin-2004-automatic-evaluation-machine-translation-quality/). In Proceedings of the 42nd annual meeting of the association for computational linguistics (ACL-04), pages 605–612.
22. Elias Lumer, Pradeep Honaganahalli Basavaraju, Myles Mason, James A Burke, and Vamse Kumar Subbiah. 2025. Graph rag-tool fusion. arXiv preprint arXiv:2502.07223. — [arXiv:2502.07223](https://arxiv.org/abs/2502.07223) [find](https://scholar.google.com/scholar?q=Elias+Lumer%2C+Pradeep+Honaganahalli+Basavaraju%2C+Myles+Mason%2C+James+A+Burke%2C+and+Vamse+Kumar+Subbiah%2E+2025%2E+Graph+rag%2Dtool+fusion%2E+arXiv+preprint+arXiv%3A2502%2E07223%2E+%E2%80%94+%5BarXiv%3A2502%2E07223%5D%28https%3A%2F%2Farxiv%2Eorg)
23. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2023. Reasoning on graphs: Faithful and interpretable large language model reasoning. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2023%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E)
24. Costas Mavromatis and George Karypis. 2024. Gnn-rag: Graph neural retrieval for large language model reasoning. [find](https://scholar.google.com/scholar?q=Costas+Mavromatis+and+George+Karypis%2E+2024%2E+Gnn%2Drag%3A+Graph+neural+retrieval+for+large+language+model+reasoning%2E)
25. Congmin Min, Sahil Bansal, Joyce Pan, Abbas Keshavarzi, Rhea Mathew, and Amar Viswanathan Kannan. 2025. Towards practical graphrag: Efficient knowledge graph construction and hybrid retrieval at scale. [find](https://scholar.google.com/scholar?q=Congmin+Min%2C+Sahil+Bansal%2C+Joyce+Pan%2C+Abbas+Keshavarzi%2C+Rhea+Mathew%2C+and+Amar+Viswanathan+Kannan%2E+2025%2E+Towards+practical+graphrag%3A+Efficient+knowledge+graph+construction+and+hybrid+retrieval+at+scale)
26. Makbule Gulcin Ozsoy, Leila Messallem, Jon Besga, and Gianandrea Minneci. 2025. Text2cypher: Bridging natural language and graph databases. In Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK), pages 100–108. [find](https://scholar.google.com/scholar?q=Makbule+Gulcin+Ozsoy%2C+Leila+Messallem%2C+Jon+Besga%2C+and+Gianandrea+Minneci%2E+2025%2E+Text2cypher%3A+Bridging+natural+language+and+graph+databases%2E+In+Proceedings+of+the+Workshop+on+Generative+AI+and+Knowledg)
27. Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, and Siliang Tang. 2025. [Graph retrieval-augmented generation: A survey](https://md.research.elamur.ai/free/en/papers/peng-2024-graph-retrieval-augmented-generation-survey/). ACM Trans. Inf. Syst., 44(2).
28. Zackary Rackauckas, Arthur Câmara, and Jakub Zavrel. 2024. Evaluating rag-fusion with ragelo: an automated elo-based framework. arXiv preprint arXiv:2406.14783. — [arXiv:2406.14783](https://arxiv.org/abs/2406.14783) [find](https://scholar.google.com/scholar?q=Zackary+Rackauckas%2C+Arthur+C%C3%A2mara%2C+and+Jakub+Zavrel%2E+2024%2E+Evaluating+rag%2Dfusion+with+ragelo%3A+an+automated+elo%2Dbased+framework%2E+arXiv+preprint+arXiv%3A2406%2E14783%2E+%E2%80%94+%5BarXiv%3A2406%2E14783%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
29. Jon Saad-Falcon, Omar Khattab, Christopher Potts, and Matei Zaharia. 2024. Ares: An automated evaluation framework for retrieval-augmented generation systems. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo… [find](https://scholar.google.com/scholar?q=Jon+Saad%2DFalcon%2C+Omar+Khattab%2C+Christopher+Potts%2C+and+Matei+Zaharia%2E+2024%2E+Ares%3A+An+automated+evaluation+framework+for+retrieval%2Daugmented+generation+systems%2E+In+Proceedings+of+the+2024+Conference+of+)
30. Daniel Sanmartin. 2024. KG-RAG: Bridging the gap between knowledge and creativity. [find](https://scholar.google.com/scholar?q=Daniel+Sanmartin%2E+2024%2E+KG%2DRAG%3A+Bridging+the+gap+between+knowledge+and+creativity%2E)
31. Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2009. The graph neural network model. IEEE Transactions on Neural Networks, 20(1):61–80. [find](https://scholar.google.com/scholar?q=Franco+Scarselli%2C+Marco+Gori%2C+Ah+Chung+Tsoi%2C+Markus+Hagenbuchner%2C+and+Gabriele+Monfardini%2E+2009%2E+The+graph+neural+network+model%2E+IEEE+Transactions+on+Neural+Networks%2C+20%281%29%3A61%E2%80%9380%2E)
32. Wei Shen, Yuhan Li, Yinan Liu, Jiawei Han, Jianyong Wang, and Xiaojie Yuan. 2021. Entity linking meets deep learning: Techniques and solutions. IEEE Transactions on Knowledge and Data Engineering, 35(3):2556–2578. [find](https://scholar.google.com/scholar?q=Wei+Shen%2C+Yuhan+Li%2C+Yinan+Liu%2C+Jiawei+Han%2C+Jianyong+Wang%2C+and+Xiaojie+Yuan%2E+2021%2E+Entity+linking+meets+deep+learning%3A+Techniques+and+solutions%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+35%28)
33. Yixuan Tang and Yi Yang. 2024. [Multihop-rag: Benchmarking retrieval-augmented generation for multi-hop queries](https://md.research.elamur.ai/free/en/papers/tang-2024-multihop-rag-benchmarking-retrieval-augmented/).
34. Yijun Tian, Huan Song, Zichen Wang, Haozhu Wang, Ziqing Hu, Fang wei Wang, Nitesh V. Chawla, and Panpan Xu. 2024. Graph neural prompting with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19208–19216. [find](https://scholar.google.com/scholar?q=Yijun+Tian%2C+Huan+Song%2C+Zichen+Wang%2C+Haozhu+Wang%2C+Ziqing+Hu%2C+Fang+wei+Wang%2C+Nitesh+V%2E+Chawla%2C+and+Panpan+Xu%2E+2024%2E+Graph+neural+prompting+with+large+language+models%2E+In+Proceedings+of+the+AAAI+Conferen)
35. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. [find](https://scholar.google.com/scholar?q=Petar+Veli%C4%8Dkovi%C4%87%2C+Guillem+Cucurull%2C+Arantxa+Casanova%2C+Adriana+Romero%2C+Pietro+Li%C3%B2%2C+and+Yoshua+Bengio%2E+2018%2E+Graph+attention+networks%2E)
36. Shu Wang, Yixiang Fang, Yingli Zhou, Xilin Liu, and Yuchi Ma. 2025. Archrag: Attributed community-based hierarchical retrieval-augmented generation. [find](https://scholar.google.com/scholar?q=Shu+Wang%2C+Yixiang+Fang%2C+Yingli+Zhou%2C+Xilin+Liu%2C+and+Yuchi+Ma%2E+2025%2E+Archrag%3A+Attributed+community%2Dbased+hierarchical+retrieval%2Daugmented+generation%2E)
37. Yilin Wen, Zifeng Wang, and Jimeng Sun. 2024. [Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models](https://md.research.elamur.ai/free/en/papers/wen-2024-mindmap-knowledge-graph-prompting-sparks/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10370–10388.
38. Yike Wu, Nan Hu, Guilin Qi, Sheng Bi, Jiaqi Ren, Aocheng Xie, and Wenting Song. 2023. Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. [find](https://scholar.google.com/scholar?q=Yike+Wu%2C+Nan+Hu%2C+Guilin+Qi%2C+Sheng+Bi%2C+Jiaqi+Ren%2C+Aocheng+Xie%2C+and+Wenting+Song%2E+2023%2E+Retrieve%2Drewrite%2Danswer%3A+A+kg%2Dto%2Dtext+enhanced+llms+framework+for+knowledge+graph+question+answering%2E)
39. Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen, Zijin Hong, Xiao Huang, and Jinsong Su. 2025. When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. [find](https://scholar.google.com/scholar?q=Zhishang+Xiang%2C+Chuanjie+Wu%2C+Qinggang+Zhang%2C+Shengyuan+Chen%2C+Zijin+Hong%2C+Xiao+Huang%2C+and+Jinsong+Su%2E+2025%2E+When+to+use+graphs+in+rag%3A+A+comprehensive+analysis+for+graph+retrieval%2Daugmented+generation%2E)
40. Yilin Xiao, Junnan Dong, Chuang Zhou, Su Dong, Qian-wen Zhang, Di Yin, Xing Sun, and Xiao Huang. 2025. Graphrag-bench: Challenging domain-specific reasoning for evaluating graph retrieval-augmented generation. arXiv preprint arXiv:2506.02404. — [arXiv:2506.02404](https://arxiv.org/abs/2506.02404) [find](https://scholar.google.com/scholar?q=Yilin+Xiao%2C+Junnan+Dong%2C+Chuang+Zhou%2C+Su+Dong%2C+Qian%2Dwen+Zhang%2C+Di+Yin%2C+Xing+Sun%2C+and+Xiao+Huang%2E+2025%2E+Graphrag%2Dbench%3A+Challenging+domain%2Dspecific+reasoning+for+evaluating+graph+retrieval%2Daugmented+ge)
41. Ziwei Xu, Sanjay Jain, and Mohan Kankanhalli. 2024. [Hallucination is inevitable: An innate limitation of large language models](https://md.research.elamur.ai/free/en/papers/xu-2024-hallucination-inevitable-innate-limitation-large/). arXiv preprint arXiv:2401.11817. *Figure 8: Semantic Agent Retriever. Mean F1 score along categories.*

*Updated 1 November 2026*