LINS: A general medical Q&A framework for enhancing the quality and credibility of LLM-generated responses
文献类型：期刊论文
| 作者 | Wang, Sheng5,6; Zhao, Fangyuan5,6; Bu, Dechao5,6; Lu, Yunwei4; Gong, Ming3; Liu, Hongjie2,6; Yang, Zhaohui5,6; Zeng, Xiaoxi1,16; Yuan, Zhiyuan13,14,15; Wan, Baoping6 |
| 刊名 | NATURE COMMUNICATIONS
 |
| 出版日期 | 2025-10-13 |
| 卷号 | 16期号:1页码:20 |
| DOI | 10.1038/s41467-025-64142-2 |
| 英文摘要 | 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models can lighten the workload of clinicians and patients, yet their responses often include fabricated evidence, outdated knowledge, and insufficient medical specificity.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. |
| 资助项目 | National Natural Science Foundation of China (National Science Foundation of China)[2022YFF1203303] ; National Key R&D Program of China[92474204] ; National Key R&D Program of China[32341019] ; National Key R&D Program of China[32070670] ; National Natural Science Foundation of China[2023030615] ; National Natural Science Foundation of China[2024020919] ; Ningbo Top Medical and Health Research Program ; Beijing Natural Science Foundation[2035] ; Beijing Natural Science Foundation[2023Z226] ; Beijing Natural Science Foundation[2024Z229] ; Ningbo Science and Technology Innovation Yongjiang ; Major Project of Guangzhou National Laboratory[KF2422-93] ; State Key Laboratory of Systems Medicine for Cancer |
| WOS研究方向 | Science & Technology - Other Topics |
| 语种 | 英语 |
| WOS记录号 | WOS:001593286500034 |
| 出版者 | NATURE PORTFOLIO |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/41618]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zhang, Hongjia; Wang, Shu; Chen, Runsheng; Zhao, Yi |
| 作者单位 | 1.Sichuan Univ, West China Hosp, West China Biomed Big Data Ctr, Chengdu, Sichuan, Peoples R China 2.Ningbo 2 Hosp, 41 Xibei Str, Ningbo, Peoples R China 3.Capital Med Univ, Beijing Anzhen Hosp, Beijing, Peoples R China 4.Peking Univ, Breast Ctr, Peoples Hosp, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Beijing, Peoples R China 6.Chinese Acad Sci, Res Ctr Ubiquitous Comp Syst, Inst Comp Technol, Beijing, Peoples R China 7.Chinese Acad Sci, Inst Biophys, Beijing, Peoples R China 8.Macau Univ Sci & Technol, Fac Med, Macau, Peoples R China 9.Sichuan Univ, West China Hosp, Mental Hlth Ctr, Chengdu, Sichuan, Peoples R China 10.Chinese Acad Sci, Inst Biophys, Key Lab Epigenet Regulat & Intervent, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Sheng,Zhao, Fangyuan,Bu, Dechao,et al. LINS: A general medical Q&A framework for enhancing the quality and credibility of LLM-generated responses[J]. NATURE COMMUNICATIONS,2025,16(1):20. |
| APA | Wang, Sheng.,Zhao, Fangyuan.,Bu, Dechao.,Lu, Yunwei.,Gong, Ming.,...&Zhao, Yi.(2025).LINS: A general medical Q&A framework for enhancing the quality and credibility of LLM-generated responses.NATURE COMMUNICATIONS,16(1),20. |
| MLA | Wang, Sheng,et al."LINS: A general medical Q&A framework for enhancing the quality and credibility of LLM-generated responses".NATURE COMMUNICATIONS 16.1(2025):20. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。