Performance Evaluation of Open-Source Large Language Models for Assisting Pathology Report Writing in Japanese
开源大语言模型在协助日文病历报告写作中的性能评估
机构 * Department of Pathology, University of Yamanashi, Chuo, Japan(山梨大学病理科) ; Division of Pathology, Exploratory Oncology Research & Clinical Trial Center, National Cancer Center, Kashiwa, Japan(国立癌症中心探索肿瘤研究与临床试验中心病理科) ; Department of Preventive Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan(东京大学医学部预防医学科) ; Department of Medical Oncology, National Cancer Center Hospital East, Kashiwa, Japan(国立癌症中心东医院医学肿瘤科) ; Department of Thoracic Surgery, National Cancer Center Hospital East, Kashiwa, Japan(国立癌症中心东医院胸外科)
专题命中 病理影像 :pathology(title,abstract);diagnosis(abstract)
AI总结 本文评估了开源大语言模型在协助日文病历报告写作中的性能,发现思维模型和医学专用模型在结构化报告和拼写纠正中表现优异,但解释性输出的偏好存在较大差异。
Comments 9 pages (including bibliography), 2 figures, 6 tables