<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arana-etal-2026-multimodal">
    <titleInfo>
        <title>Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lukas</namePart>
        <namePart type="family">Arana</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julen</namePart>
        <namePart type="family">Etxaniz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ander</namePart>
        <namePart type="family">Salaberria</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gorka</namePart>
        <namePart type="family">Azkune</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 Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource languages, comparable results remain unattained within the open science community. In this paper, we aim to develop a strong MLLM for a low-resource language, namely Basque. For that purpose, we develop our own training and evaluation image-text datasets, leveraging state-of-the-art translation systems. Using two different Large Language Models as backbones, the Llama-3.1-Instruct model and a Basque-adapted variant called Latxa, we explore several data mixtures for training, encompassing Basque and English languages for both multimodal and text-only data. Evaluating our MLLMs for close-ended and open-ended generation tasks, we show that: i) low ratios of Basque multimodal data (around 20%) are already enough to obtain solid results on Basque benchmarks, and ii) contrary to expected, a Basque instructed backbone LLM is not required to obtain a strong MLLM in Basque. Additionally, we specify the optimal data mixture strategy, the effects of multimodal data in text-only tasks, and analyze evaluation approaches for open-ended generation tasks. Our results pave the way to develop MLLMs for other low-resource languages by openly releasing our resources.</abstract>
    <identifier type="citekey">arana-etal-2026-multimodal</identifier>
    <identifier type="doi">10.63317/2ry23e89ew5v</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.721/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>9172</start>
            <end>9187</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque
%A Arana, Lukas
%A Etxaniz, Julen
%A Salaberria, Ander
%A Azkune, Gorka
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F arana-etal-2026-multimodal
%X Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource languages, comparable results remain unattained within the open science community. In this paper, we aim to develop a strong MLLM for a low-resource language, namely Basque. For that purpose, we develop our own training and evaluation image-text datasets, leveraging state-of-the-art translation systems. Using two different Large Language Models as backbones, the Llama-3.1-Instruct model and a Basque-adapted variant called Latxa, we explore several data mixtures for training, encompassing Basque and English languages for both multimodal and text-only data. Evaluating our MLLMs for close-ended and open-ended generation tasks, we show that: i) low ratios of Basque multimodal data (around 20%) are already enough to obtain solid results on Basque benchmarks, and ii) contrary to expected, a Basque instructed backbone LLM is not required to obtain a strong MLLM in Basque. Additionally, we specify the optimal data mixture strategy, the effects of multimodal data in text-only tasks, and analyze evaluation approaches for open-ended generation tasks. Our results pave the way to develop MLLMs for other low-resource languages by openly releasing our resources.
%R 10.63317/2ry23e89ew5v
%U https://aclanthology.org/2026.lrec-1.721/
%U https://doi.org/10.63317/2ry23e89ew5v
%P 9172-9187

Markdown (Informal)

[Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque](https://aclanthology.org/2026.lrec-1.721/) (Arana et al., LREC 2026)

• Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque (Arana et al., LREC 2026)

ACL

• Lukas Arana, Julen Etxaniz, Ander Salaberria, and Gorka Azkune. 2026. Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9172–9187, Palma de Mallorca, Spain. ELRA Language Resource Association.