@inproceedings{akhtar-etal-2025-2nd,
title = "The 2nd Automated Verification of Textual Claims ({AV}eri{T}e{C}) Shared Task: Open-weights, Reproducible and Efficient Systems",
author = "Akhtar, Mubashara and
Aly, Rami and
Chen, Yulong and
Deng, Zhenyun and
Schlichtkrull, Michael and
Whitehouse, Chenxi and
Vlachos, Andreas",
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-1.15/",
doi = "10.18653/v1/2025.fever-1.15",
pages = "201--223",
ISBN = "978-1-959429-53-1",
abstract = "In the First Automated Verification of Textual Claims (AVeriTeC) shared task participanting teams developed systems that for each claim retrieve evidence from the web and predict its veracity. While there was progress in automated fact-checking for real-world claims, the majority of the systems proposed relied on closed-weights large language models, which rendered them expensive to run and less reporducible. To ameliorate this issue, in this year{'}s edition of the AVERITEC shared task we required system to use only open-weights models that could be run use a single GPU with 23GBs of RAM, and that systems should take one minute or less to return verdicts accompanied by evidence retrieved from a precompiled knowledge store. The shared task received 7 submissions; 6 of which exceeded the accuracy of our baseline on the test set, while they ran in under a minute per claim on the hardware we had speficied. The winning team was CTU AIC with an AVeriTeC score of 33.17{\%}. In this paper we describe the shared task in detail and highlight key findings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhtar-etal-2025-2nd">
<titleInfo>
<title>The 2nd Automated Verification of Textual Claims (AVeriTeC) Shared Task: Open-weights, Reproducible and Efficient Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxi</namePart>
<namePart type="family">Whitehouse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</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>In the First Automated Verification of Textual Claims (AVeriTeC) shared task participanting teams developed systems that for each claim retrieve evidence from the web and predict its veracity. While there was progress in automated fact-checking for real-world claims, the majority of the systems proposed relied on closed-weights large language models, which rendered them expensive to run and less reporducible. To ameliorate this issue, in this year’s edition of the AVERITEC shared task we required system to use only open-weights models that could be run use a single GPU with 23GBs of RAM, and that systems should take one minute or less to return verdicts accompanied by evidence retrieved from a precompiled knowledge store. The shared task received 7 submissions; 6 of which exceeded the accuracy of our baseline on the test set, while they ran in under a minute per claim on the hardware we had speficied. The winning team was CTU AIC with an AVeriTeC score of 33.17%. In this paper we describe the shared task in detail and highlight key findings.</abstract>
<identifier type="citekey">akhtar-etal-2025-2nd</identifier>
<identifier type="doi">10.18653/v1/2025.fever-1.15</identifier>
<location>
<url>https://aclanthology.org/2025.fever-1.15/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>201</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The 2nd Automated Verification of Textual Claims (AVeriTeC) Shared Task: Open-weights, Reproducible and Efficient Systems
%A Akhtar, Mubashara
%A Aly, Rami
%A Chen, Yulong
%A Deng, Zhenyun
%A Schlichtkrull, Michael
%A Whitehouse, Chenxi
%A Vlachos, Andreas
%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 akhtar-etal-2025-2nd
%X In the First Automated Verification of Textual Claims (AVeriTeC) shared task participanting teams developed systems that for each claim retrieve evidence from the web and predict its veracity. While there was progress in automated fact-checking for real-world claims, the majority of the systems proposed relied on closed-weights large language models, which rendered them expensive to run and less reporducible. To ameliorate this issue, in this year’s edition of the AVERITEC shared task we required system to use only open-weights models that could be run use a single GPU with 23GBs of RAM, and that systems should take one minute or less to return verdicts accompanied by evidence retrieved from a precompiled knowledge store. The shared task received 7 submissions; 6 of which exceeded the accuracy of our baseline on the test set, while they ran in under a minute per claim on the hardware we had speficied. The winning team was CTU AIC with an AVeriTeC score of 33.17%. In this paper we describe the shared task in detail and highlight key findings.
%R 10.18653/v1/2025.fever-1.15
%U https://aclanthology.org/2025.fever-1.15/
%U https://doi.org/10.18653/v1/2025.fever-1.15
%P 201-223
Markdown (Informal)
[The 2nd Automated Verification of Textual Claims (AVeriTeC) Shared Task: Open-weights, Reproducible and Efficient Systems](https://aclanthology.org/2025.fever-1.15/) (Akhtar et al., FEVER 2025)
ACL
- Mubashara Akhtar, Rami Aly, Yulong Chen, Zhenyun Deng, Michael Schlichtkrull, Chenxi Whitehouse, and Andreas Vlachos. 2025. The 2nd Automated Verification of Textual Claims (AVeriTeC) Shared Task: Open-weights, Reproducible and Efficient Systems. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 201–223, Vienna, Austria. Association for Computational Linguistics.