@inproceedings{aula-blasco-etal-2025-veritasqa,
title = "{V}eritas{QA}: A Truthfulness Benchmark Aimed at Multilingual Transferability",
author = "Aula-Blasco, Javier and
Falc{\~a}o, J{\'u}lia and
Sotelo, Susana and
Paniagua, Silvia and
Gonzalez-Agirre, Aitor and
Villegas, Marta",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.366/",
pages = "5463--5474",
abstract = "As Large Language Models (LLMs) become available in a wider range of domains and applications, evaluating the truthfulness of multilingual LLMs is an issue of increasing relevance. TruthfulQA (Lin et al., 2022) is one of few benchmarks designed to evaluate how models imitate widespread falsehoods. However, it is strongly English-centric and starting to become outdated. We present VeritasQA, a context- and time-independent truthfulness benchmark built with multilingual transferability in mind, and available in Spanish, Catalan, Galician and English. VeritasQA comprises a set of 353 questions and answers inspired by common misconceptions and falsehoods that are not tied to any particular country or recent event. We release VeritasQA under an open license and present the evaluation results of 15 models of various architectures and sizes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aula-blasco-etal-2025-veritasqa">
<titleInfo>
<title>VeritasQA: A Truthfulness Benchmark Aimed at Multilingual Transferability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Aula-Blasco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Júlia</namePart>
<namePart type="family">Falcão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susana</namePart>
<namePart type="family">Sotelo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Paniagua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Gonzalez-Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Villegas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Large Language Models (LLMs) become available in a wider range of domains and applications, evaluating the truthfulness of multilingual LLMs is an issue of increasing relevance. TruthfulQA (Lin et al., 2022) is one of few benchmarks designed to evaluate how models imitate widespread falsehoods. However, it is strongly English-centric and starting to become outdated. We present VeritasQA, a context- and time-independent truthfulness benchmark built with multilingual transferability in mind, and available in Spanish, Catalan, Galician and English. VeritasQA comprises a set of 353 questions and answers inspired by common misconceptions and falsehoods that are not tied to any particular country or recent event. We release VeritasQA under an open license and present the evaluation results of 15 models of various architectures and sizes.</abstract>
<identifier type="citekey">aula-blasco-etal-2025-veritasqa</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.366/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5463</start>
<end>5474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VeritasQA: A Truthfulness Benchmark Aimed at Multilingual Transferability
%A Aula-Blasco, Javier
%A Falcão, Júlia
%A Sotelo, Susana
%A Paniagua, Silvia
%A Gonzalez-Agirre, Aitor
%A Villegas, Marta
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F aula-blasco-etal-2025-veritasqa
%X As Large Language Models (LLMs) become available in a wider range of domains and applications, evaluating the truthfulness of multilingual LLMs is an issue of increasing relevance. TruthfulQA (Lin et al., 2022) is one of few benchmarks designed to evaluate how models imitate widespread falsehoods. However, it is strongly English-centric and starting to become outdated. We present VeritasQA, a context- and time-independent truthfulness benchmark built with multilingual transferability in mind, and available in Spanish, Catalan, Galician and English. VeritasQA comprises a set of 353 questions and answers inspired by common misconceptions and falsehoods that are not tied to any particular country or recent event. We release VeritasQA under an open license and present the evaluation results of 15 models of various architectures and sizes.
%U https://aclanthology.org/2025.coling-main.366/
%P 5463-5474
Markdown (Informal)
[VeritasQA: A Truthfulness Benchmark Aimed at Multilingual Transferability](https://aclanthology.org/2025.coling-main.366/) (Aula-Blasco et al., COLING 2025)
ACL