@inproceedings{almutairi-etal-2024-synthetic,
title = "Synthetic {A}rabic Medical Dialogues Using Advanced Multi-Agent {LLM} Techniques",
author = "ALMutairi, Mariam and
AlKulaib, Lulwah and
Aktas, Melike and
Alsalamah, Sara and
Lu, Chang-Tien",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of the Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.2/",
doi = "10.18653/v1/2024.arabicnlp-1.2",
pages = "11--26",
abstract = "The increasing use of artificial intelligence in healthcare requires robust datasets for training and validation, particularly in the domain of medical conversations. However, the creation and accessibility of such datasets in Arabic face significant challenges, especially due to the sensitivity and privacy concerns that are associated with medical conversations. These conversations are rarely recorded or preserved, making the availability of comprehensive Arabic medical dialogue datasets scarce. This limitation slows down not only the development of effective natural language processing models but also restricts the opportunity for open comparison of algorithms and their outcomes. Recent advancements in large language models (LLMs) like ChatGPT, GPT-4, Gemini-pro, and Claude-3 show promising capabilities in generating synthetic data. To address this gap, we introduce a novel Multi-Agent LLM approach capable of generating synthetic Arabic medical dialogues from patient notes, regardless of the original language. This development presents a significant step towards overcoming the barriers in dataset availability, enhancing the potential for broader research and application in AI-driven medical dialogue systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almutairi-etal-2024-synthetic">
<titleInfo>
<title>Synthetic Arabic Medical Dialogues Using Advanced Multi-Agent LLM Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">ALMutairi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lulwah</namePart>
<namePart type="family">AlKulaib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melike</namePart>
<namePart type="family">Aktas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Alsalamah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang-Tien</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increasing use of artificial intelligence in healthcare requires robust datasets for training and validation, particularly in the domain of medical conversations. However, the creation and accessibility of such datasets in Arabic face significant challenges, especially due to the sensitivity and privacy concerns that are associated with medical conversations. These conversations are rarely recorded or preserved, making the availability of comprehensive Arabic medical dialogue datasets scarce. This limitation slows down not only the development of effective natural language processing models but also restricts the opportunity for open comparison of algorithms and their outcomes. Recent advancements in large language models (LLMs) like ChatGPT, GPT-4, Gemini-pro, and Claude-3 show promising capabilities in generating synthetic data. To address this gap, we introduce a novel Multi-Agent LLM approach capable of generating synthetic Arabic medical dialogues from patient notes, regardless of the original language. This development presents a significant step towards overcoming the barriers in dataset availability, enhancing the potential for broader research and application in AI-driven medical dialogue systems.</abstract>
<identifier type="citekey">almutairi-etal-2024-synthetic</identifier>
<identifier type="doi">10.18653/v1/2024.arabicnlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.2/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Arabic Medical Dialogues Using Advanced Multi-Agent LLM Techniques
%A ALMutairi, Mariam
%A AlKulaib, Lulwah
%A Aktas, Melike
%A Alsalamah, Sara
%A Lu, Chang-Tien
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of the Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F almutairi-etal-2024-synthetic
%X The increasing use of artificial intelligence in healthcare requires robust datasets for training and validation, particularly in the domain of medical conversations. However, the creation and accessibility of such datasets in Arabic face significant challenges, especially due to the sensitivity and privacy concerns that are associated with medical conversations. These conversations are rarely recorded or preserved, making the availability of comprehensive Arabic medical dialogue datasets scarce. This limitation slows down not only the development of effective natural language processing models but also restricts the opportunity for open comparison of algorithms and their outcomes. Recent advancements in large language models (LLMs) like ChatGPT, GPT-4, Gemini-pro, and Claude-3 show promising capabilities in generating synthetic data. To address this gap, we introduce a novel Multi-Agent LLM approach capable of generating synthetic Arabic medical dialogues from patient notes, regardless of the original language. This development presents a significant step towards overcoming the barriers in dataset availability, enhancing the potential for broader research and application in AI-driven medical dialogue systems.
%R 10.18653/v1/2024.arabicnlp-1.2
%U https://aclanthology.org/2024.arabicnlp-1.2/
%U https://doi.org/10.18653/v1/2024.arabicnlp-1.2
%P 11-26
Markdown (Informal)
[Synthetic Arabic Medical Dialogues Using Advanced Multi-Agent LLM Techniques](https://aclanthology.org/2024.arabicnlp-1.2/) (ALMutairi et al., ArabicNLP 2024)
ACL