@inproceedings{paiola-etal-2026-edubench,
title = "{E}du{B}ench: A {P}ortuguese Benchmark for Open-Ended Discursive Question Answering",
author = "Paiola, Pedro Henrique and
Mendes, Lu{\'i}s Gabriel Damiati and
Monchelato, Bruno de Oliveira and
Schuck, Andr{\'e} da Fonseca and
Garcia, Gabriel Lino and
Rodrigues, Douglas and
Caseli, Helena de Medeiros and
Papa, Jo{\~a}o Paulo",
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-1.360/",
doi = "10.63317/4nocig8f36r9",
pages = "4587--4596",
abstract = "Evaluating open-ended text generation in large language models remains challenging, particularly for non-English languages. We introduce EduBench, a comprehensive Portuguese-language benchmark comprising 3,149 discursive questions from Brazilian university entrance examinations spanning 2015{--}2025. Unlike multiple-choice or extractive QA benchmarks, EduBench requires extended, argumentative responses across diverse domains, including Humanities, Exact and Natural Sciences, and Languages. Each question includes expert-curated reference answers from official sources, rich metadata, and automated image descriptions to support text-only evaluation. We establish baseline results using nine contemporary models, ranging from 4B-parameter SLMs to state-of-the-art reasoning-capable LLMs, and evaluate them using complementary metrics (BLEU, BERTScore, G-Eval). Our results reveal substantial metric disagreement and highlight the complexity of assessing discursive generation, with models achieving 54{--}71{\%} alignment with expert answers. We release EduBench publicly to support research on Portuguese NLP and open-ended generation evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paiola-etal-2026-edubench">
<titleInfo>
<title>EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Paiola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="given">Gabriel</namePart>
<namePart type="given">Damiati</namePart>
<namePart type="family">Mendes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="given">de</namePart>
<namePart type="given">Oliveira</namePart>
<namePart type="family">Monchelato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Fonseca</namePart>
<namePart type="family">Schuck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="given">Lino</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="given">de</namePart>
<namePart type="given">Medeiros</namePart>
<namePart type="family">Caseli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Paulo</namePart>
<namePart type="family">Papa</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>Evaluating open-ended text generation in large language models remains challenging, particularly for non-English languages. We introduce EduBench, a comprehensive Portuguese-language benchmark comprising 3,149 discursive questions from Brazilian university entrance examinations spanning 2015–2025. Unlike multiple-choice or extractive QA benchmarks, EduBench requires extended, argumentative responses across diverse domains, including Humanities, Exact and Natural Sciences, and Languages. Each question includes expert-curated reference answers from official sources, rich metadata, and automated image descriptions to support text-only evaluation. We establish baseline results using nine contemporary models, ranging from 4B-parameter SLMs to state-of-the-art reasoning-capable LLMs, and evaluate them using complementary metrics (BLEU, BERTScore, G-Eval). Our results reveal substantial metric disagreement and highlight the complexity of assessing discursive generation, with models achieving 54–71% alignment with expert answers. We release EduBench publicly to support research on Portuguese NLP and open-ended generation evaluation.</abstract>
<identifier type="citekey">paiola-etal-2026-edubench</identifier>
<identifier type="doi">10.63317/4nocig8f36r9</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.360/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4587</start>
<end>4596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering
%A Paiola, Pedro Henrique
%A Mendes, Luís Gabriel Damiati
%A Monchelato, Bruno de Oliveira
%A Schuck, André da Fonseca
%A Garcia, Gabriel Lino
%A Rodrigues, Douglas
%A Caseli, Helena de Medeiros
%A Papa, João Paulo
%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 paiola-etal-2026-edubench
%X Evaluating open-ended text generation in large language models remains challenging, particularly for non-English languages. We introduce EduBench, a comprehensive Portuguese-language benchmark comprising 3,149 discursive questions from Brazilian university entrance examinations spanning 2015–2025. Unlike multiple-choice or extractive QA benchmarks, EduBench requires extended, argumentative responses across diverse domains, including Humanities, Exact and Natural Sciences, and Languages. Each question includes expert-curated reference answers from official sources, rich metadata, and automated image descriptions to support text-only evaluation. We establish baseline results using nine contemporary models, ranging from 4B-parameter SLMs to state-of-the-art reasoning-capable LLMs, and evaluate them using complementary metrics (BLEU, BERTScore, G-Eval). Our results reveal substantial metric disagreement and highlight the complexity of assessing discursive generation, with models achieving 54–71% alignment with expert answers. We release EduBench publicly to support research on Portuguese NLP and open-ended generation evaluation.
%R 10.63317/4nocig8f36r9
%U https://aclanthology.org/2026.lrec-1.360/
%U https://doi.org/10.63317/4nocig8f36r9
%P 4587-4596
Markdown (Informal)
[EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering](https://aclanthology.org/2026.lrec-1.360/) (Paiola et al., LREC 2026)
ACL
- Pedro Henrique Paiola, Luís Gabriel Damiati Mendes, Bruno de Oliveira Monchelato, André da Fonseca Schuck, Gabriel Lino Garcia, Douglas Rodrigues, Helena de Medeiros Caseli, and João Paulo Papa. 2026. EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4587–4596, Palma de Mallorca, Spain. ELRA Language Resource Association.