HiMed: Incentivizing Hindi Reasoning in Medical LLMs

Dingfeng Jiang; Han Yan; Chenze Ma; Amit Kumar Jaiswal; Ang Li; Yunxiang Jiang; Xinlei Xiong; Juhao Liang

cs.CLMay 23, 2026

HiMed: Incentivizing Hindi Reasoning in Medical LLMs

Authors: Dingfeng Jiang, Han Yan, Chenze Ma, Amit Kumar Jaiswal, Ang Li, Yunxiang Jiang, Xinlei Xiong, Juhao Liang, +7 more

Organizations: 1The Chinese University of Hong Kong, Shenzhen · 2Indian Institute of Technology (Banaras Hindu University) Varanasi · 3Tongji University · 4Shenzhen Research Institute of Big Data · 5Shenzhen Loop Area Institute · 6The Hong Kong University of Science and Technology · 7Halmstad University

Abstract

Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, their performance degrades sharply in Hindi, particularly on Indian systems of medicine. We argue that robust cross-lingual medical transfer requires Hindi reasoning. To this end, we introduce HiMed, a Hindi reasoning medical corpus and benchmark suite covering both Western and Indian medicine. We further propose HiMed-8B, a Hindi-form medical reasoning LLM, through the design of decaying scaffolding reward. Extensive experiments demonstrate improvement in Hindi medical reasoning performance and reduction in the English--Hindi accuracy gap. Ablation studies validate the contribution of each training stage and reward component. All data and code are available on GitHub: https://github.com/FreedomIntelligence/HiMed.

Explore similar work

Multilingual Medical Reasoning for Question Answering with Large Language Models
Dec 5, 2025Pietro Ferrazzi, Aitor Soroa, Rodrigo AgerriMultilingual Reasoning Clinical Reasoning
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Jun 11, 2026Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya +2Multimodal Clinical Data Multi-Modal Large Language Models
Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards
Sep 21, 2026Kalash Shah, Kunal Singh, Snehan J +1

Dec 5, 2025 · cs.CLJ/K move · Enter open · S save

Multilingual Medical Reasoning for Question Answering with Large Language Models

Pietro Ferrazzi, Aitor Soroa, Rodrigo Agerri

Fondazione Bruno Kessler, Trento, Italy · HiTZ Center - Ixa, University of the Basque Country EHU, Spain

Large Language Models (LLMs) with reasoning capabilities have recently demonstrated strong potential in medical Question Answering (QA). Existing approaches are largely English-focused and primarily rely on distillation from general-purpose LLMs, raising concerns about the reliability of their medical knowledge. In this work, we present a method to generate multilingual reasoning traces based on medical knowledge extracted from Wikipedia. We produce 500k traces in English, Italian, and Spanish, using a retrieval-augmented generation approach over medical information from Wikipedia. The traces are generated to solve medical questions drawn from MedQA and MedMCQA, which we extend to Italian and Spanish. We test our pipeline in both in-domain and out-of-domain settings across Medical QA benchmarks, and demonstrate that our reasoning traces improve performance both when utilized via in-context learning (few-shot) and supervised fine-tuning, yielding state-of-the-art results among 8B-parameter LLMs. We believe that these resources can support the development of more transparent clinical decision-support tools in multilingual settings. We release the full suite of resources: reasoning traces, translated QA datasets, Medical-Wikipedia, and fine-tuned models.

Multilingual Reasoning Clinical Reasoning Large Language Model Reasoning Multi-Hop Question Answering Benchmarks

Open paper Ask about it PDF

Abstract

Explore similar work

Multilingual Medical Reasoning for Question Answering with Large Language Models

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards