Llama 3 Challenges Proprietary State-of-the-Art Large Language Models in Radiology Board-style Examination Questions.
作者信息
Adams Lisa C, Truhn Daniel, Busch Felix, Dorfner Felix, Nawabi Jawed, Makowski Marcus R, Bressem Keno K
机构信息
From the Department of Diagnostic and Interventional Radiology, Technical University Munich, Ismaninger Str. 22, 81675 Munich, Germany (L.C.A., M.R.M., K.K.B.); Department of Radiology, University Hospital RWTH Aachen, Aachen, Germany (D.T.); Departments of Radiology (F.B., F.D.) and Neuroradiology (J.N.), Charité-Universitätsmedizin Berlin, Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany; and Department of Radiology and Nuclear Medicine, German Heart Center Munich, Munich, Germany (K.K.B.).
出版信息
Radiology. 2024 Aug;312(2):e241191. doi: 10.1148/radiol.241191.
PMID:39136566
Abstract
摘要
相似文献
1
Llama 3 Challenges Proprietary State-of-the-Art Large Language Models in Radiology Board-style Examination Questions.在放射学委员会风格的考试问题中，骆驼模型3挑战了专有的最先进大语言模型。
Radiology. 2024 Aug;312(2):e241191. doi: 10.1148/radiol.241191.
2
Large Language Models as Tools to Generate Radiology Board-Style Multiple-Choice Questions.大语言模型在生成放射科 Board 式多项选择题中的应用。
Acad Radiol. 2024 Sep;31(9):3872-3878. doi: 10.1016/j.acra.2024.06.046. Epub 2024 Jul 15.
3
Diagnostic Accuracy of Large Language Models in the European Board of Interventional Radiology Examination (EBIR) Sample Questions.大型语言模型在欧洲介入放射学委员会考试（EBIR）样题中的诊断准确性。
Cardiovasc Intervent Radiol. 2024 Jun;47(6):836-837. doi: 10.1007/s00270-024-03674-4. Epub 2024 Feb 22.
4
The Accuracy of the Multimodal Large Language Model GPT-4 on Sample Questions From the Interventional Radiology Board Examination.多模态大语言模型GPT-4在介入放射学委员会考试样题上的准确性
Acad Radiol. 2024 Aug;31(8):3476. doi: 10.1016/j.acra.2024.03.023. Epub 2024 Apr 25.
5
The performance of the multimodal large language model GPT-4 on the European board of radiology examination sample test.多模态大语言模型GPT-4在欧洲放射学会考试样本测试中的表现。
Jpn J Radiol. 2024 Aug;42(8):927. doi: 10.1007/s11604-024-01565-9. Epub 2024 Apr 3.
6
Authors' Response: The Accuracy of the Multimodal Large Language Model GPT-4 on Sample Questions From the Interventional Radiology Board Examination.作者回复：多模态大语言模型GPT-4在介入放射学委员会考试样题上的准确性
Acad Radiol. 2024 Aug;31(8):3477. doi: 10.1016/j.acra.2024.05.025. Epub 2024 Jun 21.
7
Inconsistently Accurate: Repeatability of GPT-3.5 and GPT-4 in Answering Radiology Board-style Multiple Choice Questions.准确性不一：GPT-3.5和GPT-4回答放射科委员会风格多项选择题的可重复性
Radiology. 2024 May;311(2):e241173. doi: 10.1148/radiol.241173.
8
Response to Letter to the Editor from Muhammed Said Beşler et al.: "The Performance of the Multimodal Large Language Model GPT-4 on the European Board of Radiology Examination Sample Test".对穆罕默德·赛义德·贝什勒等人致编辑信的回复：“多模态大语言模型GPT-4在欧洲放射学会考试样题测试中的表现”
Jpn J Radiol. 2024 Aug;42(8):928. doi: 10.1007/s11604-024-01577-5. Epub 2024 May 2.
9
Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance.放射学中基于检索增强的大语言模型生成：在董事会考试表现方面的又一次飞跃。
Radiology. 2024 Oct;313(1):e241489. doi: 10.1148/radiol.241489.
10
Current structure and purpose of the American Board of Radiology examination process.美国放射学会考试流程的当前结构与目的。
Acad Radiol. 2001 Dec;8(12):1260-1. doi: 10.1016/S1076-6332(03)80710-9.
引用本文的文献
1
Synthetic data trained open-source language models are feasible alternatives to proprietary models for radiology reporting.经过合成数据训练的开源语言模型是用于放射学报告的专有模型的可行替代方案。
NPJ Digit Med. 2025 Jul 23;8(1):472. doi: 10.1038/s41746-025-01658-3.
2
Comparative analysis of language models in addressing syphilis-related queries.语言模型在处理梅毒相关查询方面的比较分析。
Med Oral Patol Oral Cir Bucal. 2025 Jul 1;30(4):e551-e560. doi: 10.4317/medoral.27092.
3
Large language models for error detection in radiology reports: a comparative analysis between closed-source and privacy-compliant open-source models.用于放射学报告错误检测的大语言模型：闭源模型与符合隐私规定的开源模型的对比分析
Eur Radiol. 2025 Feb 20. doi: 10.1007/s00330-025-11438-y.
4
Benchmarking the diagnostic performance of open source LLMs in 1933 Eurorad case reports.在1933份欧洲放射学会病例报告中对开源语言模型的诊断性能进行基准测试。
NPJ Digit Med. 2025 Feb 12;8(1):97. doi: 10.1038/s41746-025-01488-3.
5
Generative AI and large language models in nuclear medicine: current status and future prospects.生成式人工智能和核医学中的大语言模型：现状与未来展望。
Ann Nucl Med. 2024 Nov;38(11):853-864. doi: 10.1007/s12149-024-01981-x. Epub 2024 Sep 25.
Zotero 插件