@inproceedings{vazquez-etal-2025-semeval,
title = "{S}em{E}val-2025 Task 3: Mu-{SHROOM}, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes",
author = {Vazquez, Raul and
Mickus, Timothee and
Zosa, Elaine and
Vahtola, Teemu and
Tiedemann, J{\"o}rg and
Sinha, Aman and
Segonne, Vincent and
Sanchez - Vega, Fernando and
Raganato, Alessandro and
Libovick{\'y}, Jind{\v{r}}ich and
Karlgren, Jussi and
Ji, Shaoxiong and
Helcl, Jind{\v{r}}ich and
Guillou, Liane and
De Gibert, Ona and
Bengoetxea, Jaione and
Attieh, Joseph and
Apidianaki, Marianna},
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-1.322/",
pages = "2472--2497",
ISBN = "979-8-89176-273-2",
abstract = "We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs).Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The very high number of submissions highlights the interest of the community in hallucination detection. We present the results of the participating systems and provide an empirical analysis in order to better understand the factors that can lead to strong performance in this task. We also underscore current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vazquez-etal-2025-semeval">
<titleInfo>
<title>SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raul</namePart>
<namePart type="family">Vazquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothee</namePart>
<namePart type="family">Mickus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaine</namePart>
<namePart type="family">Zosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teemu</namePart>
<namePart type="family">Vahtola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Segonne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Sanchez - Vega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Libovický</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jussi</namePart>
<namePart type="family">Karlgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoxiong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Helcl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liane</namePart>
<namePart type="family">Guillou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">De Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaione</namePart>
<namePart type="family">Bengoetxea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Attieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</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>We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs).Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The very high number of submissions highlights the interest of the community in hallucination detection. We present the results of the participating systems and provide an empirical analysis in order to better understand the factors that can lead to strong performance in this task. We also underscore current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans.</abstract>
<identifier type="citekey">vazquez-etal-2025-semeval</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.322/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2472</start>
<end>2497</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
%A Vazquez, Raul
%A Mickus, Timothee
%A Zosa, Elaine
%A Vahtola, Teemu
%A Tiedemann, Jörg
%A Sinha, Aman
%A Segonne, Vincent
%A Sanchez - Vega, Fernando
%A Raganato, Alessandro
%A Libovický, Jindřich
%A Karlgren, Jussi
%A Ji, Shaoxiong
%A Helcl, Jindřich
%A Guillou, Liane
%A De Gibert, Ona
%A Bengoetxea, Jaione
%A Attieh, Joseph
%A Apidianaki, Marianna
%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 vazquez-etal-2025-semeval
%X We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs).Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The very high number of submissions highlights the interest of the community in hallucination detection. We present the results of the participating systems and provide an empirical analysis in order to better understand the factors that can lead to strong performance in this task. We also underscore current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans.
%U https://aclanthology.org/2025.semeval-1.322/
%P 2472-2497
Markdown (Informal)
[SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes](https://aclanthology.org/2025.semeval-1.322/) (Vazquez et al., SemEval 2025)
ACL
- Raul Vazquez, Timothee Mickus, Elaine Zosa, Teemu Vahtola, Jörg Tiedemann, Aman Sinha, Vincent Segonne, Fernando Sanchez - Vega, Alessandro Raganato, Jindřich Libovický, Jussi Karlgren, Shaoxiong Ji, Jindřich Helcl, Liane Guillou, Ona De Gibert, Jaione Bengoetxea, Joseph Attieh, and Marianna Apidianaki. 2025. SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2472–2497, Vienna, Austria. Association for Computational Linguistics.