@inproceedings{hailemariam-etal-2025-lcteam,
title = "{LCT}eam at {S}em{E}val-2025 Task 3: Multilingual Detection of Hallucinations and Overgeneration Mistakes Using {XLM}-{R}o{BERT}a",
author = "Hailemariam, Araya and
Maldonado Rodriguez, Jose and
Ba{\c{s}}ar, Ezgi and
Kovalev, Roman and
Shcharbakova, Hanna",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.176/",
pages = "1325--1331",
ISBN = "979-8-89176-273-2",
abstract = "In recent years, the tendency of large language models to produce hallucinations has become an object of academic interest. Hallucinated or overgenerated outputs created by LLMs contain factual inaccuracies which can potentially invalidate textual coherence. The Mu-SHROOM shared task sets the goal of developing strategies for detecting hallucinated parts of LLM outputs in a multilingual context. We present an approach applicable across multiple languages, which incorporates the alignment of tokens and hard labels, as well as training a multi-lingual XLM-RoBERTa model. With this approach we managed to achieve 2nd in Chinese and top-10 positions in 7 other language tracks of the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hailemariam-etal-2025-lcteam">
<titleInfo>
<title>LCTeam at SemEval-2025 Task 3: Multilingual Detection of Hallucinations and Overgeneration Mistakes Using XLM-RoBERTa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Araya</namePart>
<namePart type="family">Hailemariam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Maldonado Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ezgi</namePart>
<namePart type="family">Başar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Kovalev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Shcharbakova</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 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>In recent years, the tendency of large language models to produce hallucinations has become an object of academic interest. Hallucinated or overgenerated outputs created by LLMs contain factual inaccuracies which can potentially invalidate textual coherence. The Mu-SHROOM shared task sets the goal of developing strategies for detecting hallucinated parts of LLM outputs in a multilingual context. We present an approach applicable across multiple languages, which incorporates the alignment of tokens and hard labels, as well as training a multi-lingual XLM-RoBERTa model. With this approach we managed to achieve 2nd in Chinese and top-10 positions in 7 other language tracks of the competition.</abstract>
<identifier type="citekey">hailemariam-etal-2025-lcteam</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.176/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1325</start>
<end>1331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LCTeam at SemEval-2025 Task 3: Multilingual Detection of Hallucinations and Overgeneration Mistakes Using XLM-RoBERTa
%A Hailemariam, Araya
%A Maldonado Rodriguez, Jose
%A Başar, Ezgi
%A Kovalev, Roman
%A Shcharbakova, Hanna
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F hailemariam-etal-2025-lcteam
%X In recent years, the tendency of large language models to produce hallucinations has become an object of academic interest. Hallucinated or overgenerated outputs created by LLMs contain factual inaccuracies which can potentially invalidate textual coherence. The Mu-SHROOM shared task sets the goal of developing strategies for detecting hallucinated parts of LLM outputs in a multilingual context. We present an approach applicable across multiple languages, which incorporates the alignment of tokens and hard labels, as well as training a multi-lingual XLM-RoBERTa model. With this approach we managed to achieve 2nd in Chinese and top-10 positions in 7 other language tracks of the competition.
%U https://aclanthology.org/2025.semeval-1.176/
%P 1325-1331
Markdown (Informal)
[LCTeam at SemEval-2025 Task 3: Multilingual Detection of Hallucinations and Overgeneration Mistakes Using XLM-RoBERTa](https://aclanthology.org/2025.semeval-1.176/) (Hailemariam et al., SemEval 2025)
ACL