dorsal/arxiv
View SchemaMed-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning
| Authors | Fan Gao, Sherry T. Tong, Jiwoong Sohn, Jiahao Huang, Junfeng Jiang, Ding Xia, Piyalitt Ittichaiwong, Kanyakorn Veerakanjana, Hyunjae Kim, Qingyu Chen, Edison Marrese Taylor, Kazuma Kobayashi, Akkiko Aizawa, Irene Li |
|---|---|
| Categories | |
| ArXiv ID | 2601.08267vv2 |
| URL | https://arxiv.org/abs/2601.08267 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.
{
"annotation_id": "4ad89058-a2cc-4423-b7df-7103a7b453a8",
"date_created": "2026-02-17T05:53:15.435000Z",
"date_modified": "2026-02-17T05:53:15.435000Z",
"file_hash": "ca4f07a7ac658855bbcc9e4b027b57b3dc469a5d5bc96d4878456900541d5ee5",
"private": false,
"record": {
"abstract": "While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.",
"arxiv_id": "2601.08267",
"authors": [
"Fan Gao",
"Sherry T. Tong",
"Jiwoong Sohn",
"Jiahao Huang",
"Junfeng Jiang",
"Ding Xia",
"Piyalitt Ittichaiwong",
"Kanyakorn Veerakanjana",
"Hyunjae Kim",
"Qingyu Chen",
"Edison Marrese Taylor",
"Kazuma Kobayashi",
"Akkiko Aizawa",
"Irene Li"
],
"categories": [
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning",
"url": "https://arxiv.org/abs/2601.08267",
"version": "v2"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "8271ae8d-2c0c-477e-b33e-88e5c3247704",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}