@inproceedings{tsoneva-etal-2026-selective,
title = "Selective Multimodal Retrieval for Automated Verification of Image{--}Text Claims",
author = "Tsoneva, Yoana and
Feig, Paul-Conrad and
Li, Jiaao and
Solopova, Veronika and
Foroutan, Neda and
Hilbert, Arthur and
Schmitt, Vera",
editor = "Akhtar, Mubashara and
Aly, Rami and
Cao, Rui 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 Ninth Fact Extraction and {VER}ification Workshop ({FEVER})",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.fever-1.10/",
pages = "127--135",
ISBN = "979-8-89176-365-4",
abstract = "This paper presents an efficiency-aware pipeline for automated fact-checking of real-world image{--}text claims that treats multimodality as a controllable design variable rather than a property that must be uniformly propagated through every stage of the system. The approach decomposes claims into verification questions, assigns each to text- or image-related types, and applies modality-aware retrieval strategies, while ultimately relying on text-only evidence for verdict prediction and justification generation. Evaluated on the AVerImaTeC dataset within the FEVER-9 shared task, the system achieves competitive question, evidence, verdict, and justification scores and ranks fourth overall, outperforming the official baseline on evidence recall, verdict accuracy, and justification quality despite not using visual evidence during retrieval. These results demonstrate that strong performance on multimodal fact-checking can be achieved by selectively controlling where visual information influences retrieval and reasoning, rather than performing full multimodal fusion at every stage of the pipeline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsoneva-etal-2026-selective">
<titleInfo>
<title>Selective Multimodal Retrieval for Automated Verification of Image–Text Claims</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoana</namePart>
<namePart type="family">Tsoneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul-Conrad</namePart>
<namePart type="family">Feig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Solopova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neda</namePart>
<namePart type="family">Foroutan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Hilbert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Schmitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth 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">Rui</namePart>
<namePart type="family">Cao</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">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-365-4</identifier>
</relatedItem>
<abstract>This paper presents an efficiency-aware pipeline for automated fact-checking of real-world image–text claims that treats multimodality as a controllable design variable rather than a property that must be uniformly propagated through every stage of the system. The approach decomposes claims into verification questions, assigns each to text- or image-related types, and applies modality-aware retrieval strategies, while ultimately relying on text-only evidence for verdict prediction and justification generation. Evaluated on the AVerImaTeC dataset within the FEVER-9 shared task, the system achieves competitive question, evidence, verdict, and justification scores and ranks fourth overall, outperforming the official baseline on evidence recall, verdict accuracy, and justification quality despite not using visual evidence during retrieval. These results demonstrate that strong performance on multimodal fact-checking can be achieved by selectively controlling where visual information influences retrieval and reasoning, rather than performing full multimodal fusion at every stage of the pipeline.</abstract>
<identifier type="citekey">tsoneva-etal-2026-selective</identifier>
<location>
<url>https://aclanthology.org/2026.fever-1.10/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>127</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Selective Multimodal Retrieval for Automated Verification of Image–Text Claims
%A Tsoneva, Yoana
%A Feig, Paul-Conrad
%A Li, Jiaao
%A Solopova, Veronika
%A Foroutan, Neda
%A Hilbert, Arthur
%A Schmitt, Vera
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Cao, Rui
%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 Ninth Fact Extraction and VERification Workshop (FEVER)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-365-4
%F tsoneva-etal-2026-selective
%X This paper presents an efficiency-aware pipeline for automated fact-checking of real-world image–text claims that treats multimodality as a controllable design variable rather than a property that must be uniformly propagated through every stage of the system. The approach decomposes claims into verification questions, assigns each to text- or image-related types, and applies modality-aware retrieval strategies, while ultimately relying on text-only evidence for verdict prediction and justification generation. Evaluated on the AVerImaTeC dataset within the FEVER-9 shared task, the system achieves competitive question, evidence, verdict, and justification scores and ranks fourth overall, outperforming the official baseline on evidence recall, verdict accuracy, and justification quality despite not using visual evidence during retrieval. These results demonstrate that strong performance on multimodal fact-checking can be achieved by selectively controlling where visual information influences retrieval and reasoning, rather than performing full multimodal fusion at every stage of the pipeline.
%U https://aclanthology.org/2026.fever-1.10/
%P 127-135
Markdown (Informal)
[Selective Multimodal Retrieval for Automated Verification of Image–Text Claims](https://aclanthology.org/2026.fever-1.10/) (Tsoneva et al., FEVER 2026)
ACL