@inproceedings{ntanavaras-etal-2026-synthetic,
title = "A Synthetic Conversational Dataset for Type 2 Diabetes Management",
author = "Ntanavaras, Stergios and
de Boer, Maaike and
Vossen, Piek T.J.M.",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.16/",
doi = "10.63317/3cbhekpxj33y",
pages = "171--181",
abstract = "Access to real patient-doctor conversations in the medical domain is often restricted due to privacy concerns, making it difficult to build robust conversational AI systems. To address this, we present a novel methodology for generating a high-quality synthetic dataset designed for conversational triple extraction in Type 2 Diabetes management. Using structured prompting with GPT-4, we generated 16 demographically and medically diverse diabetic personas, and 256 multi-turn conversations between these personas and a caretaker agent, simulating realistic and context-rich interactions. The conversations incorporate critical properties such as personalization, empathy, contextual awareness, and medically grounded advice, as validated through both LLM-based and human expert evaluations. These synthetic conversations are further annotated with Subject-Predicate-Object (SPO) labels at the token level, integrating both manual and LLM-automated methods, forming the foundation for downstream tasks like triple extraction. Our work demonstrates the feasibility of using generative AI to simulate healthcare conversations at scale, offering a solution for data-scarce domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ntanavaras-etal-2026-synthetic">
<titleInfo>
<title>A Synthetic Conversational Dataset for Type 2 Diabetes Management</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Ntanavaras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maaike</namePart>
<namePart type="family">de Boer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="given">T.J.M.</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Access to real patient-doctor conversations in the medical domain is often restricted due to privacy concerns, making it difficult to build robust conversational AI systems. To address this, we present a novel methodology for generating a high-quality synthetic dataset designed for conversational triple extraction in Type 2 Diabetes management. Using structured prompting with GPT-4, we generated 16 demographically and medically diverse diabetic personas, and 256 multi-turn conversations between these personas and a caretaker agent, simulating realistic and context-rich interactions. The conversations incorporate critical properties such as personalization, empathy, contextual awareness, and medically grounded advice, as validated through both LLM-based and human expert evaluations. These synthetic conversations are further annotated with Subject-Predicate-Object (SPO) labels at the token level, integrating both manual and LLM-automated methods, forming the foundation for downstream tasks like triple extraction. Our work demonstrates the feasibility of using generative AI to simulate healthcare conversations at scale, offering a solution for data-scarce domains.</abstract>
<identifier type="citekey">ntanavaras-etal-2026-synthetic</identifier>
<identifier type="doi">10.63317/3cbhekpxj33y</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.16/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>171</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Synthetic Conversational Dataset for Type 2 Diabetes Management
%A Ntanavaras, Stergios
%A de Boer, Maaike
%A Vossen, Piek T.J.M.
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F ntanavaras-etal-2026-synthetic
%X Access to real patient-doctor conversations in the medical domain is often restricted due to privacy concerns, making it difficult to build robust conversational AI systems. To address this, we present a novel methodology for generating a high-quality synthetic dataset designed for conversational triple extraction in Type 2 Diabetes management. Using structured prompting with GPT-4, we generated 16 demographically and medically diverse diabetic personas, and 256 multi-turn conversations between these personas and a caretaker agent, simulating realistic and context-rich interactions. The conversations incorporate critical properties such as personalization, empathy, contextual awareness, and medically grounded advice, as validated through both LLM-based and human expert evaluations. These synthetic conversations are further annotated with Subject-Predicate-Object (SPO) labels at the token level, integrating both manual and LLM-automated methods, forming the foundation for downstream tasks like triple extraction. Our work demonstrates the feasibility of using generative AI to simulate healthcare conversations at scale, offering a solution for data-scarce domains.
%R 10.63317/3cbhekpxj33y
%U https://aclanthology.org/2026.cl4health-1.16/
%U https://doi.org/10.63317/3cbhekpxj33y
%P 171-181
Markdown (Informal)
[A Synthetic Conversational Dataset for Type 2 Diabetes Management](https://aclanthology.org/2026.cl4health-1.16/) (Ntanavaras et al., CL4Health 2026)
ACL