@inproceedings{gomes-etal-2025-portuguese,
title = "{P}ortuguese Automated Fact-checking: Information Retrieval with Claim extraction",
author = "Gomes, Juliana and
Garcia, Eduardo and
Galv{\~a}o Filho, Arlindo Rodrigues",
editor = "Akhtar, Mubashara and
Aly, Rami and
Christodoulopoulos, Christos and
Cocarascu, Oana and
Guo, Zhijiang and
Mittal, Arpit and
Schlichtkrull, Michael and
Thorne, James and
Vlachos, Andreas",
booktitle = "Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.fever-1.3/",
doi = "10.18653/v1/2025.fever-1.3",
pages = "34--53",
ISBN = "978-1-959429-53-1",
abstract = "Current Portuguese Automated Fact-Checking (AFC) research often relies on datasets lacking integrated external evidence crucial for comprehensive verification. This study addresses this gap by systematically enriching Portuguese misinformation datasets. We retrieve web evidence by simulating user information-seeking behavior, guided by core claims extracted using Large Language Models (LLMs). Additionally, we apply a semi-automated validation framework to enhance dataset reliability.Our analysis reveals that inherent dataset characteristics impact data properties, evidence retrieval, and AFC model performance. While enrichment generally improves detection, its efficacy varies, influenced by challenges such as self-reinforcing online misinformation and API limitations. This work contributes enriched datasets, associating original texts with retrieved evidence and LLM-extracted claims, to foster future evidence-based fact-checking research.The code and enriched data for this study is available at https://github.com/ju-resplande/pt{\_}afc."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gomes-etal-2025-portuguese">
<titleInfo>
<title>Portuguese Automated Fact-checking: Information Retrieval with Claim extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juliana</namePart>
<namePart type="family">Gomes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arlindo</namePart>
<namePart type="given">Rodrigues</namePart>
<namePart type="family">Galvão Filho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-1-959429-53-1</identifier>
</relatedItem>
<abstract>Current Portuguese Automated Fact-Checking (AFC) research often relies on datasets lacking integrated external evidence crucial for comprehensive verification. This study addresses this gap by systematically enriching Portuguese misinformation datasets. We retrieve web evidence by simulating user information-seeking behavior, guided by core claims extracted using Large Language Models (LLMs). Additionally, we apply a semi-automated validation framework to enhance dataset reliability.Our analysis reveals that inherent dataset characteristics impact data properties, evidence retrieval, and AFC model performance. While enrichment generally improves detection, its efficacy varies, influenced by challenges such as self-reinforcing online misinformation and API limitations. This work contributes enriched datasets, associating original texts with retrieved evidence and LLM-extracted claims, to foster future evidence-based fact-checking research.The code and enriched data for this study is available at https://github.com/ju-resplande/pt_afc.</abstract>
<identifier type="citekey">gomes-etal-2025-portuguese</identifier>
<identifier type="doi">10.18653/v1/2025.fever-1.3</identifier>
<location>
<url>https://aclanthology.org/2025.fever-1.3/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>34</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Portuguese Automated Fact-checking: Information Retrieval with Claim extraction
%A Gomes, Juliana
%A Garcia, Eduardo
%A Galvão Filho, Arlindo Rodrigues
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-53-1
%F gomes-etal-2025-portuguese
%X Current Portuguese Automated Fact-Checking (AFC) research often relies on datasets lacking integrated external evidence crucial for comprehensive verification. This study addresses this gap by systematically enriching Portuguese misinformation datasets. We retrieve web evidence by simulating user information-seeking behavior, guided by core claims extracted using Large Language Models (LLMs). Additionally, we apply a semi-automated validation framework to enhance dataset reliability.Our analysis reveals that inherent dataset characteristics impact data properties, evidence retrieval, and AFC model performance. While enrichment generally improves detection, its efficacy varies, influenced by challenges such as self-reinforcing online misinformation and API limitations. This work contributes enriched datasets, associating original texts with retrieved evidence and LLM-extracted claims, to foster future evidence-based fact-checking research.The code and enriched data for this study is available at https://github.com/ju-resplande/pt_afc.
%R 10.18653/v1/2025.fever-1.3
%U https://aclanthology.org/2025.fever-1.3/
%U https://doi.org/10.18653/v1/2025.fever-1.3
%P 34-53
Markdown (Informal)
[Portuguese Automated Fact-checking: Information Retrieval with Claim extraction](https://aclanthology.org/2025.fever-1.3/) (Gomes et al., FEVER 2025)
ACL