• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

Large language models should be used as scientific reasoning engines, not knowledge databases.

作者信息

Truhn Daniel, Reis-Filho Jorge S, Kather Jakob Nikolas

机构信息

Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.

Experimental Pathology, Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.

出版信息

Nat Med. 2023 Dec;29(12):2983-2984. doi: 10.1038/s41591-023-02594-z.

DOI:10.1038/s41591-023-02594-z
PMID:37853138
Abstract
摘要

相似文献

1
Large language models should be used as scientific reasoning engines, not knowledge databases.大语言模型应被用作科学推理引擎，而非知识数据库。
Nat Med. 2023 Dec;29(12):2983-2984. doi: 10.1038/s41591-023-02594-z.
2
Logic, Probability, and Pragmatics in Syllogistic Reasoning.逻辑、概率与三段论推理中的语用学
Top Cogn Sci. 2022 Jul;14(3):574-601. doi: 10.1111/tops.12593. Epub 2022 Jan 10.
3
Covariational reasoning and item context affect language in undergraduate mass balance written explanations.变分推理和项目语境会影响大学生在物质平衡书面解释中的语言表达。
Adv Physiol Educ. 2023 Dec 1;47(4):762-775. doi: 10.1152/advan.00156.2022. Epub 2023 Aug 24.
4
Comment on Wakebe et al. (2015): Factors Accounting for Difficulties in Analogical Problem Solving.对Wakebe等人（2015年）的评论：类比问题解决困难的影响因素
Psychol Rep. 2016 Aug;119(1):309-11. doi: 10.1177/0033294116659710. Epub 2016 Jul 18.
5
Online tools help large language models to solve problems through reasoning.在线工具帮助大语言模型通过推理解决问题。
Nature. 2023 Jun;618(7965):465-466. doi: 10.1038/d41586-023-01411-4.
6
Vision-Language-Knowledge Co-Embedding for Visual Commonsense Reasoning.视觉-语言-知识共同嵌入的视觉常识推理
Sensors (Basel). 2021 Apr 21;21(9):2911. doi: 10.3390/s21092911.
7
Is relational reasoning dependent on language? A voxel-based lesion symptom mapping study.关系推理是否依赖于语言？基于体素的病变症状映射研究。
Brain Lang. 2010 May;113(2):59-64. doi: 10.1016/j.bandl.2010.01.004. Epub 2010 Mar 5.
8
How many kinds of reasoning? Inference, probability, and natural language semantics.有多少种推理方式？推理、概率和自然语言语义。
Cognition. 2015 Mar;136:123-34. doi: 10.1016/j.cognition.2014.10.016. Epub 2014 Dec 8.
9
Emergent analogical reasoning in large language models.大语言模型中的紧急类比推理。
Nat Hum Behav. 2023 Sep;7(9):1526-1541. doi: 10.1038/s41562-023-01659-w. Epub 2023 Jul 31.
10
Proportional and functional analogical reasoning in normal and language-impaired children.正常儿童和语言障碍儿童的比例与功能类比推理
J Speech Hear Disord. 1988 Nov;53(4):440-8. doi: 10.1044/jshd.5304.440.

引用本文的文献

1
The Impact of Access to Clinical Guidelines on LLM-Based Treatment Recommendations for Chronic Hepatitis B.获取临床指南对基于大语言模型的慢性乙型肝炎治疗建议的影响
Liver Int. 2025 Oct;45(10):e70324. doi: 10.1111/liv.70324.
2
Large language models for clinical decision support in gastroenterology and hepatology.用于胃肠病学和肝病学临床决策支持的大语言模型
Nat Rev Gastroenterol Hepatol. 2025 Aug 22. doi: 10.1038/s41575-025-01108-1.
3
The assessment of ChatGPT-4's performance compared to expert's consensus on chronic lateral ankle instability.

本文引用的文献

1
Large language models encode clinical knowledge.大语言模型编码临床知识。
Nature. 2023 Aug;620(7972):172-180. doi: 10.1038/s41586-023-06291-2. Epub 2023 Jul 12.
2
AI science search engines are exploding in number - are they any good?人工智能科学搜索引擎的数量正在激增——它们好用吗？
Nature. 2023 Apr;616(7958):639-640. doi: 10.1038/d41586-023-01273-w.
3
GPT-4 is here: what scientists think.GPT-4来了：科学家们的看法。
与专家共识相比，ChatGPT-4在慢性外侧踝关节不稳方面的性能评估。
J Exp Orthop. 2025 Aug 5;12(3):e70393. doi: 10.1002/jeo2.70393. eCollection 2025 Jul.
4
Enhanced pre-recruitment framework for clinical trial questionnaires through the integration of large language models and knowledge graphs.通过整合大语言模型和知识图谱增强临床试验问卷的预招募框架。
Sci Rep. 2025 Jul 28;15(1):27398. doi: 10.1038/s41598-025-11876-0.
5
Implementation of an open chemistry knowledge base with a Semantic Wiki.使用语义维基实现一个开放化学知识库。
J Cheminform. 2025 Jul 6;17(1):99. doi: 10.1186/s13321-025-01037-w.
6
RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering.RadioRAG：用于放射学问答的在线检索增强生成
Radiol Artif Intell. 2025 Jun 18:e240476. doi: 10.1148/ryai.240476.
7
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology.一种用于肿瘤学临床决策的自主人工智能代理的开发与验证。
Nat Cancer. 2025 Jun 6. doi: 10.1038/s43018-025-00991-6.
8
Automated literature research and review-generation method based on large language models.基于大语言模型的自动化文献研究与综述生成方法
Natl Sci Rev. 2025 Apr 25;12(6):nwaf169. doi: 10.1093/nsr/nwaf169. eCollection 2025 Jun.
9
Ontology-conformal recognition of materials entities using language models.使用语言模型对材料实体进行本体共形识别。
Sci Rep. 2025 May 28;15(1):18597. doi: 10.1038/s41598-025-03619-y.
10
REASONING BEYOND ACCURACY: EXPERT EVALUATION OF LARGE LANGUAGE MODELS IN DIAGNOSTIC PATHOLOGY.超越准确性的推理：诊断病理学中大型语言模型的专家评估
medRxiv. 2025 Apr 20:2025.04.11.25325686. doi: 10.1101/2025.04.11.25325686.
Nature. 2023 Mar;615(7954):773. doi: 10.1038/d41586-023-00816-5.
4
Caution with AI-generated content in biomedicine.对生物医学中人工智能生成的内容保持谨慎。
Nat Med. 2023 Mar;29(3):532. doi: 10.1038/d41591-023-00014-w.