@inproceedings{kletz-etal-2025-better,
title = "Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models",
author = "Kletz, David and
Mitrovic, Sandra and
Dolamic, Ljiljana and
Rinaldi, Fabio",
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.3/",
pages = "20--34",
ISBN = "979-8-89176-308-1",
abstract = "In this paper, we explore the potential of Open-source Small Language Models (OSLMs) for localizing hallucinations related to factual accuracy. We first present Lucifer, a dataset designed to enable proper and consistent evaluation of LMs, composed of an automatically constructed portion and a manually curated subset intended for qualitative analysis.We then assess the performance of five OSLMs using four carefully designed prompts. Results are evaluated either individually or merged through a voting-based merging approach. While our results demonstrate that the merging method yields promising performance even with smaller models, our manually curated dataset highlights the inherent difficulty of the task, underscoring the need for further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kletz-etal-2025-better">
<titleInfo>
<title>Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models</title>
</titleInfo>
<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">Sandra</namePart>
<namePart type="family">Mitrovic</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>2025-12</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>In this paper, we explore the potential of Open-source Small Language Models (OSLMs) for localizing hallucinations related to factual accuracy. We first present Lucifer, a dataset designed to enable proper and consistent evaluation of LMs, composed of an automatically constructed portion and a manually curated subset intended for qualitative analysis.We then assess the performance of five OSLMs using four carefully designed prompts. Results are evaluated either individually or merged through a voting-based merging approach. While our results demonstrate that the merging method yields promising performance even with smaller models, our manually curated dataset highlights the inherent difficulty of the task, underscoring the need for further research.</abstract>
<identifier type="citekey">kletz-etal-2025-better</identifier>
<location>
<url>https://aclanthology.org/2025.chomps-main.3/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>20</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models
%A Kletz, David
%A Mitrovic, Sandra
%A Dolamic, Ljiljana
%A Rinaldi, Fabio
%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 kletz-etal-2025-better
%X In this paper, we explore the potential of Open-source Small Language Models (OSLMs) for localizing hallucinations related to factual accuracy. We first present Lucifer, a dataset designed to enable proper and consistent evaluation of LMs, composed of an automatically constructed portion and a manually curated subset intended for qualitative analysis.We then assess the performance of five OSLMs using four carefully designed prompts. Results are evaluated either individually or merged through a voting-based merging approach. While our results demonstrate that the merging method yields promising performance even with smaller models, our manually curated dataset highlights the inherent difficulty of the task, underscoring the need for further research.
%U https://aclanthology.org/2025.chomps-main.3/
%P 20-34
Markdown (Informal)
[Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models](https://aclanthology.org/2025.chomps-main.3/) (Kletz et al., CHOMPS 2025)
ACL