@inproceedings{vykopal-etal-2026-investigating,
title = "Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection",
author = "Vykopal, Ivan and
Karamolegkou, Antonia and
Kop{\v{c}}an, Jaroslav and
Peng, Qiwei and
Jav{\r{u}}rek, Tom{\'a}{\v{s}} and
Gregor, Michal and
Simko, Marian",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.240/",
pages = "5195--5221",
ISBN = "979-8-89176-380-7",
abstract = "Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than on low-resource counterparts. We also present and inspect a novel concept - retrieval bias, when information retrieval systems tend to favor certain information over others, leaving the retrieval process skewed. In this paper, we study language and retrieval bias in the context of Previously Fact-Checked Claim Detection (PFCD). We evaluate six open-source multilingual LLMs across 20 languages using a fully multilingual prompting strategy, leveraging the AMC-16K dataset. By translating task prompts into each language, we uncover disparities in monolingual and cross-lingual performance and identify key trends based on model family, size, and prompting strategy. Our findings highlight persistent bias in LLM behavior and offer recommendations for improving equity in multilingual fact-checking. To investigate retrieval bias, we employed multilingual embedding models and look into the frequency of retrieved claims. Our analysis reveals that certain claims are retrieved disproportionately across different posts, leading to inflated retrieval performance for popular claims while under-representing less common ones."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vykopal-etal-2026-investigating">
<titleInfo>
<title>Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vykopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonia</namePart>
<namePart type="family">Karamolegkou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaroslav</namePart>
<namePart type="family">Kopčan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiwei</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Javůrek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Gregor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marian</namePart>
<namePart type="family">Simko</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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</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">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than on low-resource counterparts. We also present and inspect a novel concept - retrieval bias, when information retrieval systems tend to favor certain information over others, leaving the retrieval process skewed. In this paper, we study language and retrieval bias in the context of Previously Fact-Checked Claim Detection (PFCD). We evaluate six open-source multilingual LLMs across 20 languages using a fully multilingual prompting strategy, leveraging the AMC-16K dataset. By translating task prompts into each language, we uncover disparities in monolingual and cross-lingual performance and identify key trends based on model family, size, and prompting strategy. Our findings highlight persistent bias in LLM behavior and offer recommendations for improving equity in multilingual fact-checking. To investigate retrieval bias, we employed multilingual embedding models and look into the frequency of retrieved claims. Our analysis reveals that certain claims are retrieved disproportionately across different posts, leading to inflated retrieval performance for popular claims while under-representing less common ones.</abstract>
<identifier type="citekey">vykopal-etal-2026-investigating</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.240/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>5195</start>
<end>5221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection
%A Vykopal, Ivan
%A Karamolegkou, Antonia
%A Kopčan, Jaroslav
%A Peng, Qiwei
%A Javůrek, Tomáš
%A Gregor, Michal
%A Simko, Marian
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F vykopal-etal-2026-investigating
%X Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than on low-resource counterparts. We also present and inspect a novel concept - retrieval bias, when information retrieval systems tend to favor certain information over others, leaving the retrieval process skewed. In this paper, we study language and retrieval bias in the context of Previously Fact-Checked Claim Detection (PFCD). We evaluate six open-source multilingual LLMs across 20 languages using a fully multilingual prompting strategy, leveraging the AMC-16K dataset. By translating task prompts into each language, we uncover disparities in monolingual and cross-lingual performance and identify key trends based on model family, size, and prompting strategy. Our findings highlight persistent bias in LLM behavior and offer recommendations for improving equity in multilingual fact-checking. To investigate retrieval bias, we employed multilingual embedding models and look into the frequency of retrieved claims. Our analysis reveals that certain claims are retrieved disproportionately across different posts, leading to inflated retrieval performance for popular claims while under-representing less common ones.
%U https://aclanthology.org/2026.eacl-long.240/
%P 5195-5221
Markdown (Informal)
[Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection](https://aclanthology.org/2026.eacl-long.240/) (Vykopal et al., EACL 2026)
ACL