JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xun, Yue, Liu, Junyu, Niu, Qian, Wang, Xinyi, Yuan, Zheng, Li, Zirui, Zhang, Zequn, Zhao, Bowen, Wang, Shujun, Li, Irene, Hatakeyama-Sato, Kan, Iwasawa, Yusuke, Matsuo, Yutaka
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918528756482048
author Xun, Yue
Liu, Junyu
Niu, Qian
Wang, Xinyi
Yuan, Zheng
Li, Zirui
Zhang, Zequn
Zhao, Bowen
Wang, Shujun
Li, Irene
Hatakeyama-Sato, Kan
Iwasawa, Yusuke
Matsuo, Yutaka
author_facet Xun, Yue
Liu, Junyu
Niu, Qian
Wang, Xinyi
Yuan, Zheng
Li, Zirui
Zhang, Zequn
Zhao, Bowen
Wang, Shujun
Li, Irene
Hatakeyama-Sato, Kan
Iwasawa, Yusuke
Matsuo, Yutaka
contents We introduce JMed48k, a multi-profession Japanese healthcare licensing benchmark for evaluating vision-language models. Built from official PDF materials released by the Japanese Ministry of Health, Labour and Welfare, JMed48k contains 48,862 exam questions and 20,142 images from 11 national licensing examinations between 2005 and 2025, with visual content annotated under an 8-type taxonomy. From this corpus, we derive JMed48k-Eval, a recent five-year evaluation subset with 12,484 scored questions, including 9,905 text-only questions and 2,579 questions with images. We evaluate 21 proprietary, open-source, and medical-specific models, reporting text-only and with-image performance separately. Because these subsets contain different questions, we further introduce a paired image-removal audit that evaluates questions with images before and after removing visual content to explore four answer-transition states. The audit shows that proprietary and open source models gain substantially from images, whereas medical-specific systems show limited observable use of visual evidence, with many correct answers persisting after image removal. Even among proprietary models, the net image-removal effect varies sevenfold across professions, from +5.7 points on Physician questions to +39.8 points on Public Health Nurse questions. We release JMed48k to support reproducible, profession-stratified evaluation of vision-language models in medical licensing settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22080
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
Xun, Yue
Liu, Junyu
Niu, Qian
Wang, Xinyi
Yuan, Zheng
Li, Zirui
Zhang, Zequn
Zhao, Bowen
Wang, Shujun
Li, Irene
Hatakeyama-Sato, Kan
Iwasawa, Yusuke
Matsuo, Yutaka
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce JMed48k, a multi-profession Japanese healthcare licensing benchmark for evaluating vision-language models. Built from official PDF materials released by the Japanese Ministry of Health, Labour and Welfare, JMed48k contains 48,862 exam questions and 20,142 images from 11 national licensing examinations between 2005 and 2025, with visual content annotated under an 8-type taxonomy. From this corpus, we derive JMed48k-Eval, a recent five-year evaluation subset with 12,484 scored questions, including 9,905 text-only questions and 2,579 questions with images. We evaluate 21 proprietary, open-source, and medical-specific models, reporting text-only and with-image performance separately. Because these subsets contain different questions, we further introduce a paired image-removal audit that evaluates questions with images before and after removing visual content to explore four answer-transition states. The audit shows that proprietary and open source models gain substantially from images, whereas medical-specific systems show limited observable use of visual evidence, with many correct answers persisting after image removal. Even among proprietary models, the net image-removal effect varies sevenfold across professions, from +5.7 points on Physician questions to +39.8 points on Public Health Nurse questions. We release JMed48k to support reproducible, profession-stratified evaluation of vision-language models in medical licensing settings.
title JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.22080