@inproceedings{mitrovic-etal-2025-swushroomsia,
title = "Swushroomsia at {S}em{E}val-2025 Task 3: Probing {LLM}s' Collective Intelligence for Multilingual Hallucination Detection",
author = "Mitrovi{\'c}, Sandra and
Cornelius, Joseph and
Kletz, David and
Dolamic, Ljiljana and
Rinaldi, Fabio",
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-1.239/",
pages = "1810--1827",
ISBN = "979-8-89176-273-2",
abstract = "This paper introduces a system designed for SemEval-2025 Task 3: Mu-SHROOM, which focuses on detecting hallucinations in multilingual outputs generated by large language models (LLMs). Our approach leverages the collective intelligence of multiple LLMs by prompting several models with three distinct prompts to annotate hallucinations. These individual annotations are then merged to create a comprehensive probabilistic annotation. The proposed system demonstrates strong performance, achieving high accuracy in span detection and strong correlation between predicted probabilities and ground truth annotations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mitrovic-etal-2025-swushroomsia">
<titleInfo>
<title>Swushroomsia at SemEval-2025 Task 3: Probing LLMs’ Collective Intelligence for Multilingual Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Cornelius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Kletz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ljiljana</namePart>
<namePart type="family">Dolamic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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>This paper introduces a system designed for SemEval-2025 Task 3: Mu-SHROOM, which focuses on detecting hallucinations in multilingual outputs generated by large language models (LLMs). Our approach leverages the collective intelligence of multiple LLMs by prompting several models with three distinct prompts to annotate hallucinations. These individual annotations are then merged to create a comprehensive probabilistic annotation. The proposed system demonstrates strong performance, achieving high accuracy in span detection and strong correlation between predicted probabilities and ground truth annotations.</abstract>
<identifier type="citekey">mitrovic-etal-2025-swushroomsia</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.239/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1810</start>
<end>1827</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Swushroomsia at SemEval-2025 Task 3: Probing LLMs’ Collective Intelligence for Multilingual Hallucination Detection
%A Mitrović, Sandra
%A Cornelius, Joseph
%A Kletz, David
%A Dolamic, Ljiljana
%A Rinaldi, Fabio
%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 mitrovic-etal-2025-swushroomsia
%X This paper introduces a system designed for SemEval-2025 Task 3: Mu-SHROOM, which focuses on detecting hallucinations in multilingual outputs generated by large language models (LLMs). Our approach leverages the collective intelligence of multiple LLMs by prompting several models with three distinct prompts to annotate hallucinations. These individual annotations are then merged to create a comprehensive probabilistic annotation. The proposed system demonstrates strong performance, achieving high accuracy in span detection and strong correlation between predicted probabilities and ground truth annotations.
%U https://aclanthology.org/2025.semeval-1.239/
%P 1810-1827
Markdown (Informal)
[Swushroomsia at SemEval-2025 Task 3: Probing LLMs’ Collective Intelligence for Multilingual Hallucination Detection](https://aclanthology.org/2025.semeval-1.239/) (Mitrović et al., SemEval 2025)
ACL