Toward Global Large Language Models in Medicine
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911355321188352 |
|---|---|
| author | Yang, Rui Li, Huitao Xuan, Weihao Qi, Heli Li, Xin Yu, Kunyu Chen, Yingjian Wang, Rongrong Behmoaras, Jacques Cai, Tianxi Chakraborty, Bibhas Chen, Qingyu Cheng, Lionel Tim-Ee Damwanza, Marie-Louise Dzinotyiwei, Chido Feng, Aosong Hong, Chuan Iwasawa, Yusuke Ke, Yuhe Kitala, Linah Ko, Taehoon Lee, Jisan Li, Irene Liew, Jonathan Chong Kai Liu, Hongfang Low, Lian Leng Marrese-Taylor, Edison Matsuo, Yutaka Misi, Isheanesu Ning, Yilin Ong, Jasmine Chiat Ling Ong, Marcus Eng Hock Petretto, Enrico Rouhizadeh, Hossein Sandralegar, Abiram Schreier, Oren Tan, Iain Bee Huat Tan, Patrick Ting, Daniel Shu Wei Wang, Junjue Weng, Chunhua Wong, Matthew Yu Heng Wu, Fang Xiao, Yunze Xu, Xuhai Zeng, Qingcheng Zheng, Zhuo Peng, Yifan Teodoro, Douglas Liu, Nan |
| author_facet | Yang, Rui Li, Huitao Xuan, Weihao Qi, Heli Li, Xin Yu, Kunyu Chen, Yingjian Wang, Rongrong Behmoaras, Jacques Cai, Tianxi Chakraborty, Bibhas Chen, Qingyu Cheng, Lionel Tim-Ee Damwanza, Marie-Louise Dzinotyiwei, Chido Feng, Aosong Hong, Chuan Iwasawa, Yusuke Ke, Yuhe Kitala, Linah Ko, Taehoon Lee, Jisan Li, Irene Liew, Jonathan Chong Kai Liu, Hongfang Low, Lian Leng Marrese-Taylor, Edison Matsuo, Yutaka Misi, Isheanesu Ning, Yilin Ong, Jasmine Chiat Ling Ong, Marcus Eng Hock Petretto, Enrico Rouhizadeh, Hossein Sandralegar, Abiram Schreier, Oren Tan, Iain Bee Huat Tan, Patrick Ting, Daniel Shu Wei Wang, Junjue Weng, Chunhua Wong, Matthew Yu Heng Wu, Fang Xiao, Yunze Xu, Xuhai Zeng, Qingcheng Zheng, Zhuo Peng, Yifan Teodoro, Douglas Liu, Nan |
| contents | Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02186 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Global Large Language Models in Medicine Yang, Rui Li, Huitao Xuan, Weihao Qi, Heli Li, Xin Yu, Kunyu Chen, Yingjian Wang, Rongrong Behmoaras, Jacques Cai, Tianxi Chakraborty, Bibhas Chen, Qingyu Cheng, Lionel Tim-Ee Damwanza, Marie-Louise Dzinotyiwei, Chido Feng, Aosong Hong, Chuan Iwasawa, Yusuke Ke, Yuhe Kitala, Linah Ko, Taehoon Lee, Jisan Li, Irene Liew, Jonathan Chong Kai Liu, Hongfang Low, Lian Leng Marrese-Taylor, Edison Matsuo, Yutaka Misi, Isheanesu Ning, Yilin Ong, Jasmine Chiat Ling Ong, Marcus Eng Hock Petretto, Enrico Rouhizadeh, Hossein Sandralegar, Abiram Schreier, Oren Tan, Iain Bee Huat Tan, Patrick Ting, Daniel Shu Wei Wang, Junjue Weng, Chunhua Wong, Matthew Yu Heng Wu, Fang Xiao, Yunze Xu, Xuhai Zeng, Qingcheng Zheng, Zhuo Peng, Yifan Teodoro, Douglas Liu, Nan Computation and Language Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances. |
| title | Toward Global Large Language Models in Medicine |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.02186 |