<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-etal-2025-continued">
    <titleInfo>
        <title>Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pablo</namePart>
        <namePart type="family">Rodríguez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Silvia</namePart>
        <namePart type="given">Paniagua</namePart>
        <namePart type="family">Suárez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pablo</namePart>
        <namePart type="family">Gamallo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susana</namePart>
        <namePart type="given">Sotelo</namePart>
        <namePart type="family">Docio</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Recent advances in Large Language Models (LLMs) have led to remarkable improvements in language understanding and text generation. However, challenges remain in enhancing their performance for underrepresented languages, ensuring continual learning without catastrophic forgetting, and developing robust evaluation methodologies. This work addresses these issues by investigating the impact of Continued Pretraining (CPT) on multilingual models and proposing a comprehensive evaluation framework for LLMs, focusing on the case of Galician language. Our first contribution explores CPT strategies for languages with limited representation in multilingual models. We analyze how CPT with Galician corpora improves text generation while assessing the trade-offs between linguistic enrichment and task-solving capabilities. Our findings show that CPT with small, high-quality corpora and diverse instructions enhances both task performance and linguistic quality. Our second contribution is a structured evaluation framework based on distinguishing task-based and language-based assessments, leveraging existing and newly developed benchmarks for Galician. Additionally, we contribute new Galician LLMs, datasets for evaluation and instructions, and an evaluation framework.</abstract>
    <identifier type="citekey">rodriguez-etal-2025-continued</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.240</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.240/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>4622</start>
            <end>4637</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study
%A Rodríguez, Pablo
%A Suárez, Silvia Paniagua
%A Gamallo, Pablo
%A Docio, Susana Sotelo
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F rodriguez-etal-2025-continued
%X Recent advances in Large Language Models (LLMs) have led to remarkable improvements in language understanding and text generation. However, challenges remain in enhancing their performance for underrepresented languages, ensuring continual learning without catastrophic forgetting, and developing robust evaluation methodologies. This work addresses these issues by investigating the impact of Continued Pretraining (CPT) on multilingual models and proposing a comprehensive evaluation framework for LLMs, focusing on the case of Galician language. Our first contribution explores CPT strategies for languages with limited representation in multilingual models. We analyze how CPT with Galician corpora improves text generation while assessing the trade-offs between linguistic enrichment and task-solving capabilities. Our findings show that CPT with small, high-quality corpora and diverse instructions enhances both task performance and linguistic quality. Our second contribution is a structured evaluation framework based on distinguishing task-based and language-based assessments, leveraging existing and newly developed benchmarks for Galician. Additionally, we contribute new Galician LLMs, datasets for evaluation and instructions, and an evaluation framework.
%R 10.18653/v1/2025.findings-acl.240
%U https://aclanthology.org/2025.findings-acl.240/
%U https://doi.org/10.18653/v1/2025.findings-acl.240
%P 4622-4637

Markdown (Informal)

[Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study](https://aclanthology.org/2025.findings-acl.240/) (Rodríguez et al., Findings 2025)

• Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study (Rodríguez et al., Findings 2025)

ACL

• Pablo Rodríguez, Silvia Paniagua Suárez, Pablo Gamallo, and Susana Sotelo Docio. 2025. Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4622–4637, Vienna, Austria. Association for Computational Linguistics.