LINS: A general medical Q&A framework for enhancing the quality and credibility of LLM-generated responses

Sheng Wang, Fangyuan Zhao, Dechao Bu, Yunwei Lu, Ming Gong, Hongjie Liu, Zhaohui Yang, Xiaoxi Zeng, Zhiyuan Yuan, Baoping Wan, Jingbo Sun, Yang Wu, Lianhe Zhao, Xirun Wan, Wei Huang, Tao Wang, Mengtong Xu, Jianjun Luo, Jingjia Liu, Jianjun Zheng, Wei Zhang, Kang Zhang, Hongjia Zhang (), Shu Wang (), RunSheng Chen () and Yi Zhao ()
Additional contact information
Sheng Wang: Chinese Academy of Sciences
Fangyuan Zhao: Chinese Academy of Sciences
Dechao Bu: Chinese Academy of Sciences
Yunwei Lu: Peking University People’s Hospital
Ming Gong: Beijing Anzhen Hospital Affiliated to Capital Medical University
Hongjie Liu: Chinese Academy of Sciences
Zhaohui Yang: Chinese Academy of Sciences
Xiaoxi Zeng: Sichuan University
Zhiyuan Yuan: Fudan University
Baoping Wan: Chinese Academy of Sciences
Jingbo Sun: Chinese Academy of Sciences
Yang Wu: Chinese Academy of Sciences
Lianhe Zhao: Chinese Academy of Sciences
Xirun Wan: Center of Gynecological Oncology at Peking Union Medical College Hospital
Wei Huang: Henan Institute of Advanced Technology
Tao Wang: Henan Institute of Advanced Technology
Mengtong Xu: Chinese Academy of Sciences
Jianjun Luo: Chinese Academy of Sciences
Jingjia Liu: Ningbo No
Jianjun Zheng: Ningbo No
Wei Zhang: Sichuan University
Kang Zhang: The Macau University of Science and Technology
Hongjia Zhang: Beijing Anzhen Hospital Affiliated to Capital Medical University
Shu Wang: Peking University People’s Hospital
RunSheng Chen: University of Chinese Academy of Sciences
Yi Zhao: Chinese Academy of Sciences

Nature Communications, 2025, vol. 16, issue 1, 1-20

Abstract: Abstract Large language models can lighten the workload of clinicians and patients, yet their responses often include fabricated evidence, outdated knowledge, and insufficient medical specificity. We introduce a general retrieval-augmented question-answering framework that continuously gathers up-to-date, high-quality medical knowledge and generates evidence-traceable responses. Here we show that this approach significantly improves the evidence validity, medical expertise, and timeliness of large language model outputs, thereby enhancing their overall quality and credibility. Evaluation against 15,530 objective questions, together with two physician-curated clinical test sets covering evidence-based medical practice and medical order explanation, confirms the improvements. In blinded trials, resident physicians indicate meaningful assistance in 87.00% of evidence-based medical scenarios, and lay users find it helpful in 90.09% of medical order explanations. These findings demonstrate a practical route to trustworthy, general-purpose language assistants for clinical applications.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64142-2 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64142-2

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64142-2

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().