@inproceedings{shcharbakova-etal-2025-cross,
title = "Cross-Lingual Fact Verification: Analyzing {LLM} Performance Patterns across Languages",
author = "Shcharbakova, Hanna and
Anikina, Tatiana and
Skachkova, Natalia and
van Genabith, Josef",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.131/",
pages = "1137--1147",
abstract = "Fact verification has emerged as a critical task in combating misinformation, yet most research remains focused on English-language applications. This paper presents a comprehensive analysis of multilingual fact verification capabilities across three state-of-the-art large language models: Llama 3.1, Qwen 2.5, and Mistral Nemo. We evaluate these models on the X-Fact dataset that includes 25 typologically diverse languages, examining both seen and unseen languages through various evaluation scenarios. Our analysis employs few-shot prompting and LoRA fine-tuning approaches, revealing significant performance disparities based on script systems, with Latin script languages consistently outperforming others. We identify systematic cross-lingual instruction following failures, particularly affecting languages with non-Latin scripts. Surprisingly, some officially supported languages, such as Indonesian and Polish, which are not high-resourced languages, achieve better performance than high-resource languages like German and Spanish, challenging conventional assumptions about resource availability and model performance. The results highlight critical limitations in current multilingual LLMs for the fact verification task and provide insights for developing more inclusive multilingual systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shcharbakova-etal-2025-cross">
<titleInfo>
<title>Cross-Lingual Fact Verification: Analyzing LLM Performance Patterns across Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Shcharbakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Anikina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Skachkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fact verification has emerged as a critical task in combating misinformation, yet most research remains focused on English-language applications. This paper presents a comprehensive analysis of multilingual fact verification capabilities across three state-of-the-art large language models: Llama 3.1, Qwen 2.5, and Mistral Nemo. We evaluate these models on the X-Fact dataset that includes 25 typologically diverse languages, examining both seen and unseen languages through various evaluation scenarios. Our analysis employs few-shot prompting and LoRA fine-tuning approaches, revealing significant performance disparities based on script systems, with Latin script languages consistently outperforming others. We identify systematic cross-lingual instruction following failures, particularly affecting languages with non-Latin scripts. Surprisingly, some officially supported languages, such as Indonesian and Polish, which are not high-resourced languages, achieve better performance than high-resource languages like German and Spanish, challenging conventional assumptions about resource availability and model performance. The results highlight critical limitations in current multilingual LLMs for the fact verification task and provide insights for developing more inclusive multilingual systems.</abstract>
<identifier type="citekey">shcharbakova-etal-2025-cross</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.131/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1137</start>
<end>1147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Fact Verification: Analyzing LLM Performance Patterns across Languages
%A Shcharbakova, Hanna
%A Anikina, Tatiana
%A Skachkova, Natalia
%A van Genabith, Josef
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F shcharbakova-etal-2025-cross
%X Fact verification has emerged as a critical task in combating misinformation, yet most research remains focused on English-language applications. This paper presents a comprehensive analysis of multilingual fact verification capabilities across three state-of-the-art large language models: Llama 3.1, Qwen 2.5, and Mistral Nemo. We evaluate these models on the X-Fact dataset that includes 25 typologically diverse languages, examining both seen and unseen languages through various evaluation scenarios. Our analysis employs few-shot prompting and LoRA fine-tuning approaches, revealing significant performance disparities based on script systems, with Latin script languages consistently outperforming others. We identify systematic cross-lingual instruction following failures, particularly affecting languages with non-Latin scripts. Surprisingly, some officially supported languages, such as Indonesian and Polish, which are not high-resourced languages, achieve better performance than high-resource languages like German and Spanish, challenging conventional assumptions about resource availability and model performance. The results highlight critical limitations in current multilingual LLMs for the fact verification task and provide insights for developing more inclusive multilingual systems.
%U https://aclanthology.org/2025.ranlp-1.131/
%P 1137-1147
Markdown (Informal)
[Cross-Lingual Fact Verification: Analyzing LLM Performance Patterns across Languages](https://aclanthology.org/2025.ranlp-1.131/) (Shcharbakova et al., RANLP 2025)
ACL