@inproceedings{junqueira-etal-2026-lari,
title = "{LARI} Dataset: A Native {P}ortuguese Question Answering Dataset from Brasileiras em {PLN}",
author = "Junqueira, J{\'u}lia da Rocha and
Freitas, Larissa A. de and
Corr{\^e}a, Ulisses Brisolara",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.110/",
pages = "1055--1061",
ISBN = "979-8-89176-387-6",
abstract = "Recent advances in the field have revolutionized Question and Answering (QA). However, for languages like Portuguese, progress is often hindered by the lack of native training resources. To address this gap, this paper introduces LARI, a new dataset designed to benchmark and enhance QA in Portuguese. Our methodology combines the capabilities of the Sabi{\'a}-7B model, fine-tuned via QLoRA on a domain-specific corpus, with human validation. We utilized the book Natural Language Processing {--} Concepts, Techniques, and Applications in Portuguese (2nd Edition), as a case study for content extraction. The generated instances underwent expert human evaluation, achieving an average quality score of 4.47 out of 5. The final dataset, comprising 464 context-question-answer triples, is made publicly available to the community, offering a valuable resource for future research in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="junqueira-etal-2026-lari">
<titleInfo>
<title>LARI Dataset: A Native Portuguese Question Answering Dataset from Brasileiras em PLN</title>
</titleInfo>
<name type="personal">
<namePart type="given">Júlia</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Rocha</namePart>
<namePart type="family">Junqueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="given">A</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulisses</namePart>
<namePart type="given">Brisolara</namePart>
<namePart type="family">Corrêa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Recent advances in the field have revolutionized Question and Answering (QA). However, for languages like Portuguese, progress is often hindered by the lack of native training resources. To address this gap, this paper introduces LARI, a new dataset designed to benchmark and enhance QA in Portuguese. Our methodology combines the capabilities of the Sabiá-7B model, fine-tuned via QLoRA on a domain-specific corpus, with human validation. We utilized the book Natural Language Processing – Concepts, Techniques, and Applications in Portuguese (2nd Edition), as a case study for content extraction. The generated instances underwent expert human evaluation, achieving an average quality score of 4.47 out of 5. The final dataset, comprising 464 context-question-answer triples, is made publicly available to the community, offering a valuable resource for future research in low-resource settings.</abstract>
<identifier type="citekey">junqueira-etal-2026-lari</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.110/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>1055</start>
<end>1061</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LARI Dataset: A Native Portuguese Question Answering Dataset from Brasileiras em PLN
%A Junqueira, Júlia da Rocha
%A Freitas, Larissa A. de
%A Corrêa, Ulisses Brisolara
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F junqueira-etal-2026-lari
%X Recent advances in the field have revolutionized Question and Answering (QA). However, for languages like Portuguese, progress is often hindered by the lack of native training resources. To address this gap, this paper introduces LARI, a new dataset designed to benchmark and enhance QA in Portuguese. Our methodology combines the capabilities of the Sabiá-7B model, fine-tuned via QLoRA on a domain-specific corpus, with human validation. We utilized the book Natural Language Processing – Concepts, Techniques, and Applications in Portuguese (2nd Edition), as a case study for content extraction. The generated instances underwent expert human evaluation, achieving an average quality score of 4.47 out of 5. The final dataset, comprising 464 context-question-answer triples, is made publicly available to the community, offering a valuable resource for future research in low-resource settings.
%U https://aclanthology.org/2026.propor-1.110/
%P 1055-1061
Markdown (Informal)
[LARI Dataset: A Native Portuguese Question Answering Dataset from Brasileiras em PLN](https://aclanthology.org/2026.propor-1.110/) (Junqueira et al., PROPOR 2026)
ACL