@inproceedings{sinha-etal-2025-shroom,
title = "{SHROOM}-{CAP}: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications",
author = "Sinha, Aman and
Gamba, Federica and
V{\'a}zquez, Ra{\'u}l and
Mickus, Timothee and
Chattopadhyay, Ahana and
Zanella, Laura and
Arakkal Remesh, Binesh and
Kankanampati, Yash and
Chandramania, Aryan and
Agarwal, Rohit",
editor = {Sinha, Aman and
V{\'a}zquez, Ra{\'u}l and
Mickus, Timothee and
Agarwal, Rohit and
Buhnila, Ioana and
Schmidtov{\'a}, Patr{\'i}cia and
Gamba, Federica and
Prasad, Dilip K. and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.chomps-main.7/",
doi = "10.18653/v1/2025.chomps-main.7",
pages = "70--80",
ISBN = "979-8-89176-308-1",
abstract = "This paper presents an overview of the SHROOM-CAP Shared Task, which focuses on detecting hallucinations and over-generation errors in cross-lingual analyses of scientific publications. SHROOM-CAP covers nine languages: five high-resource (English, French, Hindi, Italian, and Spanish) and four low-resource (Bengali, Gujarati, Malayalam, and Telugu). The task frames hallucination detection as a binary classification problem, where participants must predict whether a given text contains factual inaccuracies and fluency mistakes. We received 1,571 submissions from 5 participating teams during the test phase over the nine languages. In the paper, we present an analysis of the evaluated systems to assess their performance on the hallucination detection task across languages. Our findings reveal a disparity in system performance between high-resource and low-resource languages. Furthermore, we observe that factuality and fluency tend to be closely aligned in high-resource languages, whereas this correlation is less evident in low-resource languages. Overall, SHROOM-CAP underlines that hallucination detection remains a challenging open problem, particularly in low-resource and domain-specific settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sinha-etal-2025-shroom">
<titleInfo>
<title>SHROOM-CAP: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications</title>
</titleInfo>
<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">Federica</namePart>
<namePart type="family">Gamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</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">Ahana</namePart>
<namePart type="family">Chattopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Zanella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binesh</namePart>
<namePart type="family">Arakkal Remesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Kankanampati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aryan</namePart>
<namePart type="family">Chandramania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothee</namePart>
<namePart type="family">Mickus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Buhnila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Gamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilip</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-308-1</identifier>
</relatedItem>
<abstract>This paper presents an overview of the SHROOM-CAP Shared Task, which focuses on detecting hallucinations and over-generation errors in cross-lingual analyses of scientific publications. SHROOM-CAP covers nine languages: five high-resource (English, French, Hindi, Italian, and Spanish) and four low-resource (Bengali, Gujarati, Malayalam, and Telugu). The task frames hallucination detection as a binary classification problem, where participants must predict whether a given text contains factual inaccuracies and fluency mistakes. We received 1,571 submissions from 5 participating teams during the test phase over the nine languages. In the paper, we present an analysis of the evaluated systems to assess their performance on the hallucination detection task across languages. Our findings reveal a disparity in system performance between high-resource and low-resource languages. Furthermore, we observe that factuality and fluency tend to be closely aligned in high-resource languages, whereas this correlation is less evident in low-resource languages. Overall, SHROOM-CAP underlines that hallucination detection remains a challenging open problem, particularly in low-resource and domain-specific settings.</abstract>
<identifier type="citekey">sinha-etal-2025-shroom</identifier>
<identifier type="doi">10.18653/v1/2025.chomps-main.7</identifier>
<location>
<url>https://aclanthology.org/2025.chomps-main.7/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>70</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SHROOM-CAP: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications
%A Sinha, Aman
%A Gamba, Federica
%A Vázquez, Raúl
%A Mickus, Timothee
%A Chattopadhyay, Ahana
%A Zanella, Laura
%A Arakkal Remesh, Binesh
%A Kankanampati, Yash
%A Chandramania, Aryan
%A Agarwal, Rohit
%Y Sinha, Aman
%Y Vázquez, Raúl
%Y Mickus, Timothee
%Y Agarwal, Rohit
%Y Buhnila, Ioana
%Y Schmidtová, Patrícia
%Y Gamba, Federica
%Y Prasad, Dilip K.
%Y Tiedemann, Jörg
%S Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-308-1
%F sinha-etal-2025-shroom
%X This paper presents an overview of the SHROOM-CAP Shared Task, which focuses on detecting hallucinations and over-generation errors in cross-lingual analyses of scientific publications. SHROOM-CAP covers nine languages: five high-resource (English, French, Hindi, Italian, and Spanish) and four low-resource (Bengali, Gujarati, Malayalam, and Telugu). The task frames hallucination detection as a binary classification problem, where participants must predict whether a given text contains factual inaccuracies and fluency mistakes. We received 1,571 submissions from 5 participating teams during the test phase over the nine languages. In the paper, we present an analysis of the evaluated systems to assess their performance on the hallucination detection task across languages. Our findings reveal a disparity in system performance between high-resource and low-resource languages. Furthermore, we observe that factuality and fluency tend to be closely aligned in high-resource languages, whereas this correlation is less evident in low-resource languages. Overall, SHROOM-CAP underlines that hallucination detection remains a challenging open problem, particularly in low-resource and domain-specific settings.
%R 10.18653/v1/2025.chomps-main.7
%U https://aclanthology.org/2025.chomps-main.7/
%U https://doi.org/10.18653/v1/2025.chomps-main.7
%P 70-80
Markdown (Informal)
[SHROOM-CAP: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications](https://aclanthology.org/2025.chomps-main.7/) (Sinha et al., CHOMPS 2025)
ACL
- Aman Sinha, Federica Gamba, Raúl Vázquez, Timothee Mickus, Ahana Chattopadhyay, Laura Zanella, Binesh Arakkal Remesh, Yash Kankanampati, Aryan Chandramania, and Rohit Agarwal. 2025. SHROOM-CAP: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications. In Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025), pages 70–80, Mumbai, India. Association for Computational Linguistics.