@inproceedings{lopez-ponce-etal-2025-gil,
title = "{GIL}-{IIMAS} {UNAM} at {S}em{E}val-2025 Task 3: {M}e{SSI}: A Multilmodule System to detect hallucinated Segments in trivia-like Inquiries.",
author = "L{\'o}pez-Ponce, Francisco and
Salas-Jimenez, Karla and
Ju{\'a}rez-P{\'e}rez, Adri{\'a}n and
Hern{\'a}ndez-Bustamante, Diego and
Bel-Enguix, Gemma and
G{\'o}mez-Adorno, Helena",
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-1.208/",
pages = "1577--1584",
ISBN = "979-8-89176-273-2",
abstract = "We present MeSSI, a multi-module system applied to SemEval 2025{'}s task 3: Mu-SHROOM. Our system tags questions in order to obtain semantic relevant terms that are used as information retrieval characteristics. Said characteristics serve as extraction terms for Wikipedia pages that are in turn processed to generate gold standard texts used in a hallucination evaluation system. A PoST-based entity comparison was implemented to contrast the test dataset sentences with the corresponding generated gold standards, wich in turn was the main criteria to tag hallucinations, partitioned in soft labels and hard labels. This method was tested in Spanish and English, finishing 18th and 19th respectively on the IoU based ranking."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-ponce-etal-2025-gil">
<titleInfo>
<title>GIL-IIMAS UNAM at SemEval-2025 Task 3: MeSSI: A Multilmodule System to detect hallucinated Segments in trivia-like Inquiries.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">López-Ponce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karla</namePart>
<namePart type="family">Salas-Jimenez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrián</namePart>
<namePart type="family">Juárez-Pérez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Hernández-Bustamante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Bel-Enguix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gómez-Adorno</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 MeSSI, a multi-module system applied to SemEval 2025’s task 3: Mu-SHROOM. Our system tags questions in order to obtain semantic relevant terms that are used as information retrieval characteristics. Said characteristics serve as extraction terms for Wikipedia pages that are in turn processed to generate gold standard texts used in a hallucination evaluation system. A PoST-based entity comparison was implemented to contrast the test dataset sentences with the corresponding generated gold standards, wich in turn was the main criteria to tag hallucinations, partitioned in soft labels and hard labels. This method was tested in Spanish and English, finishing 18th and 19th respectively on the IoU based ranking.</abstract>
<identifier type="citekey">lopez-ponce-etal-2025-gil</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.208/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1577</start>
<end>1584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GIL-IIMAS UNAM at SemEval-2025 Task 3: MeSSI: A Multilmodule System to detect hallucinated Segments in trivia-like Inquiries.
%A López-Ponce, Francisco
%A Salas-Jimenez, Karla
%A Juárez-Pérez, Adrián
%A Hernández-Bustamante, Diego
%A Bel-Enguix, Gemma
%A Gómez-Adorno, Helena
%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 lopez-ponce-etal-2025-gil
%X We present MeSSI, a multi-module system applied to SemEval 2025’s task 3: Mu-SHROOM. Our system tags questions in order to obtain semantic relevant terms that are used as information retrieval characteristics. Said characteristics serve as extraction terms for Wikipedia pages that are in turn processed to generate gold standard texts used in a hallucination evaluation system. A PoST-based entity comparison was implemented to contrast the test dataset sentences with the corresponding generated gold standards, wich in turn was the main criteria to tag hallucinations, partitioned in soft labels and hard labels. This method was tested in Spanish and English, finishing 18th and 19th respectively on the IoU based ranking.
%U https://aclanthology.org/2025.semeval-1.208/
%P 1577-1584
Markdown (Informal)
[GIL-IIMAS UNAM at SemEval-2025 Task 3: MeSSI: A Multilmodule System to detect hallucinated Segments in trivia-like Inquiries.](https://aclanthology.org/2025.semeval-1.208/) (López-Ponce et al., SemEval 2025)
ACL