# BiMediX: Bilingual Medical Mixture of Experts LLM

Source: [BiMediX: Bilingual Medical Mixture of Experts LLM](<https://www.sota2.com/research/paper/68fa762e1e209131cea6bb3a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:48:32.506Z

Authors: Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan, Timothy Baldwin, Hisham Cholakkal

Published: 2024-02-20T18:59:26.000Z

## Abstract

In this paper, we introduce BiMediX, the first bilingual medical mixture of experts LLM designed for seamless interaction in both English and Arabic. Our model facilitates a wide range of medical interactions in English and Arabic, including multi-turn chats to inquire about additional details such as patient symptoms and medical history, multiple-choice question answering, and open-ended question answering. We propose a semi-automated English-to-Arabic translation pipeline with human refinement to ensure high-quality translations. We also introduce a comprehensive evaluation benchmark for Arabic medical LLMs. Furthermore, we introduce BiMed1.3M, an extensive Arabic-English bilingual instruction set covering 1.3 Million diverse medical interactions, resulting in over 632 million healthcare specialized tokens for instruction tuning. Our BiMed1.3M dataset includes 250k synthesized multi-turn doctor-patient chats and maintains a 1:2 Arabic-to-English ratio. Our model outperforms state-of-the-art Med42 and Meditron by average absolute gains of 2.5% and 4.1%, respectively, computed across multiple medical evaluation benchmarks in English, while operating at 8-times faster inference. Moreover, our BiMediX outperforms the generic Arabic-English bilingual LLM, Jais-30B, by average absolute gains of 10% on our Arabic medical benchmark and 15% on bilingual evaluations across multiple datasets. Our project page with source code and trained model is available at https://github.com/mbzuai-oryx/BiMediX .

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.13253>)

[PDF](<https://arxiv.org/pdf/2402.13253.pdf>)