@inproceedings{sauri-etal-2026-small,
title = "Small Language Models for Less-Resourced Languages in a Real-World Scenario: The Case for {C}atalan",
author = "Saur{\'i}, Roser and
S{\`a}nchez-Ferreres, Josep and
Padro, Lluis and
Carmona, Josep",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.27/",
doi = "10.63317/4qn4qiyiwuze",
pages = "270--279",
abstract = "Small Language Models (SLMs), typically ranging from a few million to 10{--}15 billion parameters, offer a promising solution towards constraints imposed by platform size{--}particularly mobile and IoT devices{--}and by the requirements of many organizations such as SMEs, which need solutions that ensure data privacy while remaining cost-effective. Their compactness and efficiency provide digital sovereignty and flexibility, though with more limited general-purpose capabilities. This makes them especially sensitive when working with underrepresented languages, such as Catalan, due to interference from majority languages that can increase bias risk. This paper evaluates state-of-the-art SLMs in a real-world Catalan use case: an AI assistant for older adults, assessing both user interactions and structured function call generation. Our work, which contributes to the Anonymized-Project initiative for deploying a connected SLM-based infrastructure under the Model Context Protocol, demonstrates that some SLMs are able to deliver high-quality performance even in resource-constrained, linguistically minority environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sauri-etal-2026-small">
<titleInfo>
<title>Small Language Models for Less-Resourced Languages in a Real-World Scenario: The Case for Catalan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roser</namePart>
<namePart type="family">Saurí</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Sànchez-Ferreres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluis</namePart>
<namePart type="family">Padro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Carmona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Small Language Models (SLMs), typically ranging from a few million to 10–15 billion parameters, offer a promising solution towards constraints imposed by platform size–particularly mobile and IoT devices–and by the requirements of many organizations such as SMEs, which need solutions that ensure data privacy while remaining cost-effective. Their compactness and efficiency provide digital sovereignty and flexibility, though with more limited general-purpose capabilities. This makes them especially sensitive when working with underrepresented languages, such as Catalan, due to interference from majority languages that can increase bias risk. This paper evaluates state-of-the-art SLMs in a real-world Catalan use case: an AI assistant for older adults, assessing both user interactions and structured function call generation. Our work, which contributes to the Anonymized-Project initiative for deploying a connected SLM-based infrastructure under the Model Context Protocol, demonstrates that some SLMs are able to deliver high-quality performance even in resource-constrained, linguistically minority environments.</abstract>
<identifier type="citekey">sauri-etal-2026-small</identifier>
<identifier type="doi">10.63317/4qn4qiyiwuze</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.27/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>270</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Small Language Models for Less-Resourced Languages in a Real-World Scenario: The Case for Catalan
%A Saurí, Roser
%A Sànchez-Ferreres, Josep
%A Padro, Lluis
%A Carmona, Josep
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F sauri-etal-2026-small
%X Small Language Models (SLMs), typically ranging from a few million to 10–15 billion parameters, offer a promising solution towards constraints imposed by platform size–particularly mobile and IoT devices–and by the requirements of many organizations such as SMEs, which need solutions that ensure data privacy while remaining cost-effective. Their compactness and efficiency provide digital sovereignty and flexibility, though with more limited general-purpose capabilities. This makes them especially sensitive when working with underrepresented languages, such as Catalan, due to interference from majority languages that can increase bias risk. This paper evaluates state-of-the-art SLMs in a real-world Catalan use case: an AI assistant for older adults, assessing both user interactions and structured function call generation. Our work, which contributes to the Anonymized-Project initiative for deploying a connected SLM-based infrastructure under the Model Context Protocol, demonstrates that some SLMs are able to deliver high-quality performance even in resource-constrained, linguistically minority environments.
%R 10.63317/4qn4qiyiwuze
%U https://aclanthology.org/2026.sigul-1.27/
%U https://doi.org/10.63317/4qn4qiyiwuze
%P 270-279
Markdown (Informal)
[Small Language Models for Less-Resourced Languages in a Real-World Scenario: The Case for Catalan](https://aclanthology.org/2026.sigul-1.27/) (Saurí et al., SIGUL-EURALI-DCLRL 2026)
ACL