@inproceedings{farber-etal-2026-medpt,
title = "{M}ed{PT}: A Massive Medical Question Answering Dataset for {B}razilian-{P}ortuguese Speakers",
author = "Farber, Fernanda Bufon and
Brito, Iago Alves and
Dollis, Julia Soares and
Ribeiro, Pedro Schindler Freire Brasil and
Sousa, Rafael Teixeira and
Galv{\~a}o Filho, Arlindo R.",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.190/",
doi = "10.63317/5mrjjtbsf6rv",
pages = "2419--2429",
abstract = "While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages. This creates a critical barrier for other languages, as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus of patient-doctor interactions for the Brazilian Portuguese medical domain. Comprising 384,095 authentic question-answer pairs and covering over 3,200 distinct health-related conditions, the dataset was refined through a rigorous multi-stage curation protocol that employed a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries, resulting in a corpus of approximately 57 million tokens. We further utilize of LLM-driven annotation to classify queries into seven semantic types to capture user intent. To validate MedPT{'}s utility, we benchmark it in a medical specialty classification task: fine-tuning a 1.7B parameter model achieves an outstanding 94{\%} F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset{'}s deep semantic richness. We publicly release MedPT on Hugging Face to support the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farber-etal-2026-medpt">
<titleInfo>
<title>MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernanda</namePart>
<namePart type="given">Bufon</namePart>
<namePart type="family">Farber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iago</namePart>
<namePart type="given">Alves</namePart>
<namePart type="family">Brito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="given">Soares</namePart>
<namePart type="family">Dollis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Schindler</namePart>
<namePart type="given">Freire</namePart>
<namePart type="given">Brasil</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Teixeira</namePart>
<namePart type="family">Sousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arlindo</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Galvão Filho</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages. This creates a critical barrier for other languages, as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus of patient-doctor interactions for the Brazilian Portuguese medical domain. Comprising 384,095 authentic question-answer pairs and covering over 3,200 distinct health-related conditions, the dataset was refined through a rigorous multi-stage curation protocol that employed a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries, resulting in a corpus of approximately 57 million tokens. We further utilize of LLM-driven annotation to classify queries into seven semantic types to capture user intent. To validate MedPT’s utility, we benchmark it in a medical specialty classification task: fine-tuning a 1.7B parameter model achieves an outstanding 94% F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset’s deep semantic richness. We publicly release MedPT on Hugging Face to support the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world.</abstract>
<identifier type="citekey">farber-etal-2026-medpt</identifier>
<identifier type="doi">10.63317/5mrjjtbsf6rv</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.190/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2419</start>
<end>2429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers
%A Farber, Fernanda Bufon
%A Brito, Iago Alves
%A Dollis, Julia Soares
%A Ribeiro, Pedro Schindler Freire Brasil
%A Sousa, Rafael Teixeira
%A Galvão Filho, Arlindo R.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F farber-etal-2026-medpt
%X While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages. This creates a critical barrier for other languages, as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus of patient-doctor interactions for the Brazilian Portuguese medical domain. Comprising 384,095 authentic question-answer pairs and covering over 3,200 distinct health-related conditions, the dataset was refined through a rigorous multi-stage curation protocol that employed a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries, resulting in a corpus of approximately 57 million tokens. We further utilize of LLM-driven annotation to classify queries into seven semantic types to capture user intent. To validate MedPT’s utility, we benchmark it in a medical specialty classification task: fine-tuning a 1.7B parameter model achieves an outstanding 94% F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset’s deep semantic richness. We publicly release MedPT on Hugging Face to support the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world.
%R 10.63317/5mrjjtbsf6rv
%U https://aclanthology.org/2026.lrec-1.190/
%U https://doi.org/10.63317/5mrjjtbsf6rv
%P 2419-2429
Markdown (Informal)
[MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers](https://aclanthology.org/2026.lrec-1.190/) (Farber et al., LREC 2026)
ACL