西安交大联合团队提出 Hyper-RAG 方法登 Nature Communications

Acknowledgements

　　This work was supported by the Brain Science and Brain-like Intelligence Technology — National Science and Technology Major Project (2025ZD0217300 [Y.G.]), Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China under Grant No. JYB2025XDXM504 [N.Z.], the Beijing Natural Science Foundation (No. L242167 [Y.G.]), the National Natural Science Foundation of China under Grant (No. 623B2066 [Y.F.], U24A20252 [S.D.], 62125305 [S.D.], 62088102 [Y.G.], 62021002 [Y.G.], 12531019 [S.Y.]), the Noncommunicable Chronic Diseases — National Science and Technology Major Project (2025ZD0552500 [Y.F.]; 2025ZD0552505 [Y.F.]), the Joint Funds of the National Natural Science Foundation of China No. U2336211 [H.H.], National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University (No. HMHAI-202412 [Y.G.]), the Fundamental Research Funds for the Central Universities under Grant No. xtr062025010 [S.D.]. Additionally, we thank Xizhe Yu for his contributions to the development of the Hyper-RAG visualization system.

Author information

Author notes

　　These authors contributed equally: Yifan Feng, Hao Hu, Shihui Ying.

Authors and Affiliations

1. {School of Software, BNRist, THUIBCS, BLBCI}, Tsinghua University, Beijing, China
   Yifan Feng & Yue Gao
2. Yangtze Delta Region Institute, Tsinghua University, Jiaxing, China
   Yifan Feng & Yue Gao
3. State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, and Institute of Artificial Intelligence and Robotics, Xiʼan Jiaotong University, Xiʼan, China
   Hao Hu, Shiquan Liu, Shaoyi Du & Nanning Zheng
4. Department of Ultrasound, the Second Affiliated Hospital of Xiʼan Jiaotong University, Xiʼan, China
   Hao Hu & Shaoyi Du
5. Shanghai Institute of Applied Mathematics and Mechanics, School of Mechanics and Engineering Science, Shanghai University, Shanghai, China
   Shihui Ying
6. School of Software Engineering, Xiʼan Jiaotong University, Xiʼan, China
   Xingliang Hou
7. Newchase (Shanghai) Pharmaceutical Technology Co. Ltd., Shanghai, China
   Mingyuan Yang
8. Shenzhen Clinical Research Center for Mental Disorders, Shenzhen Kangning Hospital and Shenzhen Mental Health Center, Shenzhen, China
   Junchang Li
9. School of Information and Electronics, Beijing Institute of Technology, Beijing, China
   Han Hu

Authors

1. Yifan Feng
2. Hao Hu
3. Shihui Ying
4. Xingliang Hou
5. Shiquan Liu
6. Mingyuan Yang
7. Junchang Li
8. Shaoyi Du
9. Nanning Zheng
10. Han Hu
11. Yue Gao

Corresponding authors

　　Correspondence to Shaoyi Du, Nanning Zheng, Han Hu or Yue Gao.

Ethics declarations

Competing interests

　　The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information (download PDF)

Transparent Peer Review file (download PDF)

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

About this article

Cite this article

　　Feng, Y., Hu, H., Ying, S. et al. Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation.
Nat Commun (2026). https://doi.org/10.1038/s41467-026-71411-1

Share this article

　　Anyone you share the following link with will be able to read this content:

　　Get shareable link

　　Provided by the Springer Nature SharedIt content-sharing initiative

Subjects

• Computational science
• Computer science
• Information theory and computation