---
title: "Medical Graph RAG — paper by Wu et al. (2025)"
description: "LLMs used in medicine have two weaknesses. 52 references, cited by 12 papers here. Among them: 79."
authors: ["Junde Wu", "Jiayuan Zhu", "Yunli Qi", "Jingkun Chen", "Min Xu", "Filippo Menolascina", "Yueming Jin", "Vicente Grau"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.1381/"
doi: "10.18653/v1/2025.acl-long.1381"
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/wu-2025-medical-graph-rag-evidence-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2025-medical-graph-rag-evidence-based/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/) / Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation

# Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation

**Authors:** [Junde Wu](https://md.research.elamur.ai/free/en/authors/junde-wu/), [Jiayuan Zhu](https://md.research.elamur.ai/free/en/authors/jiayuan-zhu/), Yunli Qi, Jingkun Chen, [Min Xu](https://md.research.elamur.ai/free/en/authors/min-xu/), Filippo Menolascina, [Yueming Jin](https://md.research.elamur.ai/free/en/authors/yueming-jin/) and Vicente Grau · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **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/2025.acl-long.1381/) · [PDF](https://aclanthology.org/2025.acl-long.1381.pdf) · [DOI 10.18653/v1/2025.acl-long.1381](https://doi.org/10.18653/v1/2025.acl-long.1381) · [OpenAlex](https://openalex.org/W4412889782)

**Citations:** 79 citations (OpenAlex, 2026-10-14) · [12](https://md.research.elamur.ai/free/en/papers/wu-2025-medical-graph-rag-evidence-based/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLMs used in medicine have two weaknesses. Domain knowledge is too large to fit in a context window, and fine-tuning closed commercial models is often impossible. They may also distort established facts in ways that non-experts cannot easily detect. MedGraphRAG addresses both problems by adapting GraphRAG to the medical domain.

During Triple Graph Construction, entities extracted from user documents are linked to a fixed repository graph. This graph has two layers: medical books and papers, and the UMLS vocabulary. Each user entity thus forms a [RAG entity, source, definition] triple, so answers can be traced back to sources and official definitions.

Instead of GraphRAG's expensive community building, U-Retrieval summarizes graphs with predefined medical tags and clusters them into a hierarchy. It finds the relevant graph top-down, then refines the answer bottom-up using broader tags.

The authors tested the method with GPT, Gemini and LLaMA on medical Q&A, fact-checking and long-form generation tasks. It beat classic RAG, GraphRAG and many medically fine-tuned LLMs, and clinicians judged its answers more reliable and better grounded in evidence.

## Key points
- **Evaluation:** 9 medical Q&A benchmarks, 2 health fact-checking datasets, a long-form generation test set, and a clinician human evaluation (120 MultiMedQA questions, 50 Diverse-Health questions). The authors report new SOTA results on all Q&A benchmarks.
- **Graph construction:** Documents are split with LangChain semantic chunking (buffer size 5). Entity types come from UMLS semantic types. Cross-layer links ("the reference of", "the definition of") are created when embedding cosine similarity exceeds a threshold.
- **Tagging and clustering:** Tags follow ASTM electronic health record categories such as Symptoms, Patient History, Body Functions and Medication. Graphs are grouped by agglomerative clustering with a dynamic threshold that merges the top 20% most similar pairs, up to 12 layers.
- **Retrieval depth:** The best setting was 4 layers for GPT-4 and 5 layers for other models.
- **Limitations:** Graph construction is computationally costly, and answering takes about 70 seconds per question. Hyper-parameters were chosen empirically on limited data.

*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 (8): [🖥️ 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 · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 263 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 260 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 214 works

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

## Cite

Cite as: Junde Wu, Jiayuan Zhu, Yunli Qi, Jingkun Chen, Min Xu, Filippo Menolascina, Yueming Jin and Vicente Grau. 2025. Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation. 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.

```bibtex
@inproceedings{wu2025medical,
  title = {{Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation}},
  author = {Junde Wu, Jiayuan Zhu, Yunli Qi, Jingkun Chen, Min Xu, Filippo Menolascina, Yueming Jin and Vicente Grau},
  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.1381},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1381}
}
```

- [← previous Data Interpreter: An LLM Agent for Data Science](https://md.research.elamur.ai/free/en/papers/hong-2025-data-interpreter-llm-agent-data/)
- [next → Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://md.research.elamur.ai/free/en/papers/liu-2025-culturally-aware-adapted-nlp-taxonomy/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/)

## References

52 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Olivier Bodenreider. 2004. The unified medical language system (umls): integrating biomedical terminology. Nucleic acids research, 32(suppl_1):D267– D270. [find](https://scholar.google.com/scholar?q=Olivier+Bodenreider%2E+2004%2E+The+unified+medical+language+system+%28umls%29%3A+integrating+biomedical+terminology%2E+Nucleic+acids+research%2C+32%28suppl%5F1%29%3AD267%E2%80%93+D270%2E)
2. Bernd Bohnet, Vinh Q. Tran, Pat Verga, Roee Aharoni, Daniel Andor, Livio Baldini Soares, Massimiliano Ciaramita, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, Kai Hui, Tom Kwiatkowski, Ji Ma, Jianmo Ni, Lierni Sestorain Saralegui, Tal Schuster, William W. Cohen, Michael Collins, Dipanjan Das, D… — [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://md.research.elamur.ai/free/en/papers/bohnet-2022-attributed-question-answering-evaluation-modeling/)
3. Elliot Bolton, David Hall, Michihiro Yasunaga, Tony Lee, Chris Manning, and Percy Liang. 2022. Biomedlm. Stanford Center for Research on Foundation Models. [find](https://scholar.google.com/scholar?q=Elliot+Bolton%2C+David+Hall%2C+Michihiro+Yasunaga%2C+Tony+Lee%2C+Chris+Manning%2C+and+Percy+Liang%2E+2022%2E+Biomedlm%2E+Stanford+Center+for+Research+on+Foundation+Models%2E)
4. Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, and Dong Yu. 2023. [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://md.research.elamur.ai/free/en/papers/chen-2024-dense-x-retrieval-what-retrieval/) arXiv preprint. ArXiv:2312.06648 [cs].
5. Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2024. GRAG: Graph Retrieval-Augmented Generation. arXiv preprint. ArXiv:2405.16506 [cs]. [find](https://scholar.google.com/scholar?q=Yuntong+Hu%2C+Zhihan+Lei%2C+Zheng+Zhang%2C+Bo+Pan%2C+Chen+Ling%2C+and+Liang+Zhao%2E+2024%2E+GRAG%3A+Graph+Retrieval%2DAugmented+Generation%2E+arXiv+preprint%2E+ArXiv%3A2405%2E16506+%5Bcs%5D%2E)
6. Enyan Dai, Yiwei Sun, and Suhang Wang. 2020. Ginger cannot cure cancer: Battling fake health news with a comprehensive data repository. arXiv preprint arXiv:2002.00837. — [arXiv:2002.00837](https://arxiv.org/abs/2002.00837) [find](https://scholar.google.com/scholar?q=Enyan+Dai%2C+Yiwei+Sun%2C+and+Suhang+Wang%2E+2020%2E+Ginger+cannot+cure+cancer%3A+Battling+fake+health+news+with+a+comprehensive+data+repository%2E+arXiv+preprint+arXiv%3A2002%2E00837%2E+%E2%80%94+%5BarXiv%3A2002%2E00837%5D%28https%3A%2F%2Far)
7. Minbyul Jeong, Jiwoong Sohn, Mujeen Sung, and Jaewoo Kang. 2024. [Improving medical reasoning through retrieval and self-reflection with retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/jeong-2024-improving-medical-reasoning-through-retrieval/). Bioinformatics, 40(Supplement_1):i119–i129.
8. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024a. 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+and+Jonathan+Larson%2E+2024a%2E+From+local+to+global%3A+A+graph+rag+approach+to+query%2Dfocused+summarization%2E+arXiv)
9. Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2021. [What disease does this patient have? a large-scale open domain question answering dataset from medical exams](https://md.research.elamur.ai/free/en/papers/jin-2020-disease-this-patient-have-large/). Applied Sciences, 11(14):6421.
10. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024b. From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv preprint. ArXiv:2404.16130 [cs]. [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+and+Jonathan+Larson%2E+2024b%2E+From+Local+to+Global%3A+A+Graph+RAG+Approach+to+Query%2DFocused+Summarization%2E+arXiv)
11. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. 2019. [Pubmedqa: A dataset for biomedical research question answering](https://md.research.elamur.ai/free/en/papers/jin-2019-pubmedqa-dataset-biomedical-research-question/). arXiv preprint arXiv:1909.06146.
12. Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. 2023a. [RARR: Researching and Revising What Language Models Say, Using Language Models](https://md.research.elamur.ai/free/en/papers/gao-2023-rarr-researching-revising-what-language/). In Proceedings of the 61st Annual Meeting of the Associat…
13. Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023b. [Enabling large language models to generate text with citations](https://md.research.elamur.ai/free/en/papers/gao-2023-enabling-large-language-models-generate/). arXiv preprint arXiv:2305.14627.
14. Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023c. [Enabling Large Language Models to Generate Text with Citations](https://md.research.elamur.ai/free/en/papers/gao-2023-enabling-large-language-models-generate/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6465–6488, Singapore. Association for Computational Linguistics.
15. Qiao Jin, Won Kim, Qingyu Chen, Donald C Comeau, Lana Yeganova, W John Wilbur, and Zhiyong Lu. 2023. Medcpt: Contrastive pre-trained transformers with large-scale pubmed search logs for zero-shot biomedical information retrieval. Bioinformatics, 39(11):btad651. [find](https://scholar.google.com/scholar?q=Qiao+Jin%2C+Won+Kim%2C+Qingyu+Chen%2C+Donald+C+Comeau%2C+Lana+Yeganova%2C+W+John+Wilbur%2C+and+Zhiyong+Lu%2E+2023%2E+Medcpt%3A+Contrastive+pre%2Dtrained+transformers+with+large%2Dscale+pubmed+search+logs+for+zero%2Dshot+biom)
16. Alistair EW Johnson, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J Pollard, Sicheng Hao, Benjamin Moody, Brian Gow, et al. 2023. [Mimic-iv, a freely accessible electronic health record dataset](https://md.research.elamur.ai/free/en/papers/johnson-2023-mimic-iv-freely-accessible-electronic/). Scientific data, 10(1):1.
17. Neema Kotonya and Francesca Toni. 2020. [Explainable automated fact-checking for public health claims](https://md.research.elamur.ai/free/en/papers/kotonya-2020-explainable-automated-fact-checking-public/). arXiv preprint arXiv:2010.09926. langchain. 2024. Enhancing rag-based application accuracy by constructing and leveraging knowledge graphs. [https://blog.langchain.dev/enhancing-rag-based-application…](https://blog.langchain.dev/enhancing-rag-based-application…) [↗](https://blog.langchain.dev/enhancing-rag-based-application…)
18. Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, and Hoifung Poon. 2022. [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://md.research.elamur.ai/free/en/papers/gu-2020-domain-specific-language-model-pretraining/). ACM Transactions on Computing for Healthcare, 3(1):1–23. ArXiv:2007.15779 [cs].
19. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2021. [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). arXiv preprint. ArXiv:2005.11401 [cs].
20. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. [REALM: Retrieval-Augmented Language Model Pre-Training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). arXiv preprint. ArXiv:2002.08909 [cs].
21. Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, and Deheng Ye. 2024. [More agents is all you need](https://md.research.elamur.ai/free/en/papers/li-2024-more-agents-all-need/). Preprint, arXiv:2402.05120.
22. Ali Hadi, Edward Tran, Branavan Nagarajan, and Amrit Kirpalani. 2024. Evaluation of chatgpt as a diagnostic tool for medical learners and clinicians. Plos one, 19(7):e0307383. [find](https://scholar.google.com/scholar?q=Ali+Hadi%2C+Edward+Tran%2C+Branavan+Nagarajan%2C+and+Amrit+Kirpalani%2E+2024%2E+Evaluation+of+chatgpt+as+a+diagnostic+tool+for+medical+learners+and+clinicians%2E+Plos+one%2C+19%287%29%3Ae0307383%2E)
23. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). arXiv preprint arXiv:2009.03300.
24. Cui Long, Yongbin Liu, Chunping Ouyang, and Ying Yu. 2024. Bailicai: A domain-optimized retrieval-augmented generation framework for medical applications. arXiv preprint arXiv:2407.21055. — [arXiv:2407.21055](https://arxiv.org/abs/2407.21055) [find](https://scholar.google.com/scholar?q=Cui+Long%2C+Yongbin+Liu%2C+Chunping+Ouyang%2C+and+Ying+Yu%2E+2024%2E+Bailicai%3A+A+domain%2Doptimized+retrieval%2Daugmented+generation+framework+for+medical+applications%2E+arXiv+preprint+arXiv%3A2407%2E21055%2E+%E2%80%94+%5BarXiv%3A240)
25. Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. Biogpt: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics, 23(6):bbac409. [find](https://scholar.google.com/scholar?q=Renqian+Luo%2C+Liai+Sun%2C+Yingce+Xia%2C+Tao+Qin%2C+Sheng+Zhang%2C+Hoifung+Poon%2C+and+Tie%2DYan+Liu%2E+2022%2E+Biogpt%3A+generative+pre%2Dtrained+transformer+for+biomedical+text+generation+and+mining%2E+Briefings+in+bioinfo)
26. Jing Miao, Charat Thongprayoon, Supawadee Sup-padungsuk, Oscar A Garcia Valencia, and Wisit Che-ungpasitporn. 2024. Integrating retrieval-augmented generation with large language models in nephrology: advancing practical applications. Medicina, 60(3):445. microsoft. 2024. Microsoft azure graphrag. h… [find](https://scholar.google.com/scholar?q=Jing+Miao%2C+Charat+Thongprayoon%2C+Supawadee+Sup%2Dpadungsuk%2C+Oscar+A+Garcia+Valencia%2C+and+Wisit+Che%2Dungpasitporn%2E+2024%2E+Integrating+retrieval%2Daugmented+generation+with+large+language+models+in+nephrology%3A)
27. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. 2021. [WebGPT: Browser-assis…](https://md.research.elamur.ai/free/en/papers/nakano-2021-webgpt-browser-assisted-question-answering/)
28. Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, and Eric Horvitz. 2023. Can Generalist Foundation Mod… [find](https://scholar.google.com/scholar?q=Harsha+Nori%2C+Yin+Tat+Lee%2C+Sheng+Zhang%2C+Dean+Carignan%2C+Richard+Edgar%2C+Nicolo+Fusi%2C+Nicholas+King%2C+Jonathan+Larson%2C+Yuanzhi+Li%2C+Weishung+Liu%2C+Renqian+Luo%2C+Scott+Mayer+McKinney%2C+Robert+Osazuwa+Ness%2C+Hoif)
29. OpenAI. 2023a. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). Preprint, arXiv:2303.08774.
30. OpenAI. 2023b. Openai. introducing chatgpt. [https://openai.com/blog/chatgpt/](https://openai.com/blog/chatgpt/). [↗](https://openai.com/blog/chatgpt/)
31. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. [Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering](https://md.research.elamur.ai/free/en/papers/pal-2022-medmcqa-large-scale-multi-subject/). In Conference on health, inference, and learning, pages 248–260. PMLR.
32. Jirui Qi, Gabriele Sarti, Raquel Fernández, and Arianna Bisazza. 2024. Model internals-based answer attribution for trustworthy retrieval-augmented generation. arXiv preprint arXiv:2406.13663. [find](https://scholar.google.com/scholar?q=Jirui+Qi%2C+Gabriele+Sarti%2C+Raquel+Fern%C3%A1ndez%2C+and+Arianna+Bisazza%2E+2024%2E+Model+internals%2Dbased+answer+attribution+for+trustworthy+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2406%2E13663%2E)
33. Khaled Saab, Tao Tu, Wei-Hung Weng, Ryutaro Tanno, David Stutz, Ellery Wulczyn, Fan Zhang, Tim Strother, Chunjong Park, Elahe Vedadi, et al. 2024. [Capabilities of gemini models in medicine](https://md.research.elamur.ai/free/en/papers/saab-2024-capabilities-gemini-models-medicine/). arXiv preprint arXiv:2404.18416.
34. Thomas Savage, Ashwin Nayak, Robert Gallo, Ekanath Rangan, and Jonathan H Chen. 2024. Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. NPJ Digital Medicine, 7(1):20. [find](https://scholar.google.com/scholar?q=Thomas+Savage%2C+Ashwin+Nayak%2C+Robert+Gallo%2C+Ekanath+Rangan%2C+and+Jonathan+H+Chen%2E+2024%2E+Diagnostic+reasoning+prompts+reveal+the+potential+for+large+language+model+interpretability+in+medicine%2E+NPJ+Digit)
35. Tobias Schimanski, Jingwei Ni, Mathias Kraus, Elliott Ash, and Markus Leippold. 2024. Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1913– 193… [find](https://scholar.google.com/scholar?q=Tobias+Schimanski%2C+Jingwei+Ni%2C+Mathias+Kraus%2C+Elliott+Ash%2C+and+Markus+Leippold%2E+2024%2E+Towards+Faithful+and+Robust+LLM+Specialists+for+Evidence%2DBased+Question%2DAnswering%2E+In+Proceedings+of+the+62nd+Annu)
36. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. 2022. [Large language models encode clinical knowledge](https://md.research.elamur.ai/free/en/papers/singhal-2022-large-language-models-encode-clinical/). arXiv preprint arXiv:2212.13138.
37. Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, Stephen Pfohl, Heather Cole-Lewis, Darlene Neal, Mike Schaekermann, Amy Wang, Mohamed Amin, Sami Lachgar, Philip Mansfield, Sushant Prakash, Bradley Green, Ewa Dominowska, Blaise Aguera y Arcas, Nenad Tomasev, Y… — [Towards Expert-Level Medical Question Answering with Large Language Models](https://md.research.elamur.ai/free/en/papers/singhal-2023-towards-expert-level-medical-question/)
38. Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, Stephen Pfohl, Heather Cole-Lewis, Darlene Neal, et al. 2023b. [Towards expert-level medical question answering with large language models](https://md.research.elamur.ai/free/en/papers/singhal-2023-towards-expert-level-medical-question/). arXiv preprint arXiv:2305.09617.
39. Aviv Slobodkin, Eran Hirsch, Arie Cattan, Tal Schuster, and Ido Dagan. 2024. [Attribute first, then generate: Locally-attributable grounded text generation](https://md.research.elamur.ai/free/en/papers/slobodkin-2024-attribute-first-then-generate-locally/). arXiv preprint arXiv:2403.17104.
40. Eric E Smith and Andrew E Beaudin. 2018. New insights into cerebral small vessel disease and vascular cognitive impairment from mri. Current opinion in neurology, 31(1):36–43. [find](https://scholar.google.com/scholar?q=Eric+E+Smith+and+Andrew+E+Beaudin%2E+2018%2E+New+insights+into+cerebral+small+vessel+disease+and+vascular+cognitive+impairment+from+mri%2E+Current+opinion+in+neurology%2C+31%281%29%3A36%E2%80%9343%2E)
41. Jiwoong Sohn, Yein Park, Chanwoong Yoon, Sihyeon Park, Hyeon Hwang, Mujeen Sung, Hyunjae Kim, and Jaewoo Kang. 2024. Rationale-guided retrieval augmented generation for medical question answering. arXiv preprint arXiv:2411.00300. [find](https://scholar.google.com/scholar?q=Jiwoong+Sohn%2C+Yein+Park%2C+Chanwoong+Yoon%2C+Sihyeon+Park%2C+Hyeon+Hwang%2C+Mujeen+Sung%2C+Hyunjae+Kim%2C+and+Jaewoo+Kang%2E+2024%2E+Rationale%2Dguided+retrieval+augmented+generation+for+medical+question+answering%2E+arX)
42. Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. 2023. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805.
43. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [LLaMA: Open and Efficient Foundation Language Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv pr…
44. Jiaqi Wang, Enze Shi, Sigang Yu, Zihao Wu, Chong Ma, Haixing Dai, Qiushi Yang, Yanqing Kang, Jinru Wu, Huawen Hu, et al. 2023. Prompt engineering for healthcare: Methodologies and applications. arXiv preprint arXiv:2304.14670. — [arXiv:2304.14670](https://arxiv.org/abs/2304.14670) [find](https://scholar.google.com/scholar?q=Jiaqi+Wang%2C+Enze+Shi%2C+Sigang+Yu%2C+Zihao+Wu%2C+Chong+Ma%2C+Haixing+Dai%2C+Qiushi+Yang%2C+Yanqing+Kang%2C+Jinru+Wu%2C+Huawen+Hu%2C+et+al%2E+2023%2E+Prompt+engineering+for+healthcare%3A+Methodologies+and+applications%2E+arXiv+)
45. Christopher YK Williams, Brenda Y Miao, Aaron E Kornblith, and Atul J Butte. 2024. Evaluating the use of large language models to provide clinical recommendations in the emergency department. Nature Communications, 15(1):8236. [find](https://scholar.google.com/scholar?q=Christopher+YK+Williams%2C+Brenda+Y+Miao%2C+Aaron+E+Kornblith%2C+and+Atul+J+Butte%2E+2024%2E+Evaluating+the+use+of+large+language+models+to+provide+clinical+recommendations+in+the+emergency+department%2E+Nature+C)
46. Chaoyi Wu, Weixiong Lin, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. [PMC-LLaMA: Towards Building Open-source Language Models for Medicine](https://md.research.elamur.ai/free/en/papers/wu-2023-pmc-llama-towards-building-open/). arXiv preprint. ArXiv:2304.14454 [cs].
47. Yunfei Xie, Juncheng Wu, Haoqin Tu, Siwei Yang, Bingchen Zhao, Yongshuo Zong, Qiao Jin, Cihang Xie, and Yuyin Zhou. 2024. A preliminary study of o1 in medicine: Are we closer to an ai doctor? arXiv preprint arXiv:2409.15277. — [arXiv:2409.15277](https://arxiv.org/abs/2409.15277) [find](https://scholar.google.com/scholar?q=Yunfei+Xie%2C+Juncheng+Wu%2C+Haoqin+Tu%2C+Siwei+Yang%2C+Bingchen+Zhao%2C+Yongshuo+Zong%2C+Qiao+Jin%2C+Cihang+Xie%2C+and+Yuyin+Zhou%2E+2024%2E+A+preliminary+study+of+o1+in+medicine%3A+Are+we+closer+to+an+ai+doctor%3F+arXiv+pr)
48. Guangzhi Xiong, Qiao Jin, Zhiyong Lu, and Aidong Zhang. 2024. [Benchmarking retrieval-augmented generation for medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/). arXiv preprint arXiv:2402.13178.
49. Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D. Manning, Percy Liang, and Jure Leskovec. 2022a. Deep Bidirectional Language-Knowledge Graph Pretraining. arXiv preprint. ArXiv:2210.09338 [cs]. [find](https://scholar.google.com/scholar?q=Michihiro+Yasunaga%2C+Antoine+Bosselut%2C+Hongyu+Ren%2C+Xikun+Zhang%2C+Christopher+D%2E+Manning%2C+Percy+Liang%2C+and+Jure+Leskovec%2E+2022a%2E+Deep+Bidirectional+Language%2DKnowledge+Graph+Pretraining%2E+arXiv+preprint%2E+A)
50. Michihiro Yasunaga, Jure Leskovec, and Percy Liang. 2022b. [LinkBERT: Pretraining Language Models with Document Links](https://md.research.elamur.ai/free/en/papers/yasunaga-2022-linkbert-pretraining-language-models-document/). arXiv preprint. ArXiv:2203.15827 [cs].
51. Jiajie Zhang, Yushi Bai, Xin Lv, Wanjun Gu, Danqing Liu, Minhao Zou, Shulin Cao, Lei Hou, Yuxiao Dong, Ling Feng, et al. 2024. Longcite: Enabling llms to generate fine-grained citations in long-context qa. arXiv e-prints, pages arXiv–2409. [find](https://scholar.google.com/scholar?q=Jiajie+Zhang%2C+Yushi+Bai%2C+Xin+Lv%2C+Wanjun+Gu%2C+Danqing+Liu%2C+Minhao+Zou%2C+Shulin+Cao%2C+Lei+Hou%2C+Yuxiao+Dong%2C+Ling+Feng%2C+et+al%2E+2024%2E+Longcite%3A+Enabling+llms+to+generate+fine%2Dgrained+citations+in+long%2Dcontex)
52. 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)

*Updated 2 November 2026*