@inproceedings{pieri-etal-2024-bimedix,
title = "{B}i{M}edi{X}: Bilingual Medical Mixture of Experts {LLM}",
author = "Pieri, Sara and
Mullappilly, Sahal Shaji and
Khan, Fahad and
Anwer, Rao and
Khan, Salman and
Baldwin, Timothy and
Cholakkal, Hisham",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.989",
pages = "16984--17002",
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 that covers 1.3 Million diverse medical interactions, including 200k synthesized multi-turn doctor-patient chats, in 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 and 15{\%} on our bilingual evaluations across multiple datasets. Additionally, BiMediX exceeds the accuracy of GPT4 by 4.4{\%} in open-ended question UPHILL evaluation and largely outperforms state-of-the-art open source medical LLMs in human evaluations of multi-turn conversations. Our trained models, instruction set, and source code are available at https://github.com/mbzuai-oryx/BiMediX.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pieri-etal-2024-bimedix">
<titleInfo>
<title>BiMediX: Bilingual Medical Mixture of Experts LLM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Pieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahal</namePart>
<namePart type="given">Shaji</namePart>
<namePart type="family">Mullappilly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rao</namePart>
<namePart type="family">Anwer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hisham</namePart>
<namePart type="family">Cholakkal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 that covers 1.3 Million diverse medical interactions, including 200k synthesized multi-turn doctor-patient chats, in 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 and 15% on our bilingual evaluations across multiple datasets. Additionally, BiMediX exceeds the accuracy of GPT4 by 4.4% in open-ended question UPHILL evaluation and largely outperforms state-of-the-art open source medical LLMs in human evaluations of multi-turn conversations. Our trained models, instruction set, and source code are available at https://github.com/mbzuai-oryx/BiMediX.</abstract>
<identifier type="citekey">pieri-etal-2024-bimedix</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.989</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>16984</start>
<end>17002</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BiMediX: Bilingual Medical Mixture of Experts LLM
%A Pieri, Sara
%A Mullappilly, Sahal Shaji
%A Khan, Fahad
%A Anwer, Rao
%A Khan, Salman
%A Baldwin, Timothy
%A Cholakkal, Hisham
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F pieri-etal-2024-bimedix
%X 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 that covers 1.3 Million diverse medical interactions, including 200k synthesized multi-turn doctor-patient chats, in 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 and 15% on our bilingual evaluations across multiple datasets. Additionally, BiMediX exceeds the accuracy of GPT4 by 4.4% in open-ended question UPHILL evaluation and largely outperforms state-of-the-art open source medical LLMs in human evaluations of multi-turn conversations. Our trained models, instruction set, and source code are available at https://github.com/mbzuai-oryx/BiMediX.
%U https://aclanthology.org/2024.findings-emnlp.989
%P 16984-17002
Markdown (Informal)
[BiMediX: Bilingual Medical Mixture of Experts LLM](https://aclanthology.org/2024.findings-emnlp.989) (Pieri et al., Findings 2024)
ACL
- Sara Pieri, Sahal Shaji Mullappilly, Fahad Khan, Rao Anwer, Salman Khan, Timothy Baldwin, and Hisham Cholakkal. 2024. BiMediX: Bilingual Medical Mixture of Experts LLM. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16984–17002, Miami, Florida, USA. Association for Computational Linguistics.