<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azurmendi-etal-2026-automatic">
    <titleInfo>
        <title>Automatic Essay Scoring and Feedback Generation in Basque Language Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ekhi</namePart>
        <namePart type="family">Azurmendi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xabier</namePart>
        <namePart type="family">Arregi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Oier</namePart>
        <namePart type="family">Lopez de Lacalle</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>This paper introduces the first publicly available dataset for Automatic Essay Scoring (AES) and feedback generation in Basque, targeting the CEFR C1 proficiency level. The dataset comprises 3,200 essays from HABE, each annotated by expert evaluators with criterion specific scores covering correctness, richness, coherence, cohesion, and task alignment enriched with detailed feedback and error examples. We fine-tune open-source models, including RoBERTa-EusCrawl and Latxa 8B/70B, for scoring. We focused on correctness criteria for the explanation generation, adapting Latxa to correctly predict both, scores and explanations. Our experiments show that encoder models remain highly reliable for AES, while supervised fine-tuning (SFT) of Latxa significantly enhances performance, surpassing state-of-the-art (SoTA) closed-source systems such as GPT-5 and Claude Sonnet 4.5 in scoring consistency and feedback quality. We also propose a novel evaluation methodology for assessing feedback generation, combining automatic consistency metrics with expert-based validation of extracted learner errors. Results demonstrate that the fine-tuned Latxa model produces criterion-aligned, pedagogically meaningful feedback and identifies a wider range of error types than proprietary models. This resource and benchmark establish a foundation for transparent, reproducible, and educationally grounded NLP research in low-resource languages such as Basque. The dataset, models and manual evalution results are available here: https://huggingface.co/collections/EkhiAzur/habe-hitz-c1</abstract>
    <identifier type="citekey">azurmendi-etal-2026-automatic</identifier>
    <identifier type="doi">10.63317/2vf49six8jhv</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.54/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>735</start>
            <end>746</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Automatic Essay Scoring and Feedback Generation in Basque Language Learning
%A Azurmendi, Ekhi
%A Arregi, Xabier
%A Lopez de Lacalle, Oier
%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 azurmendi-etal-2026-automatic
%X This paper introduces the first publicly available dataset for Automatic Essay Scoring (AES) and feedback generation in Basque, targeting the CEFR C1 proficiency level. The dataset comprises 3,200 essays from HABE, each annotated by expert evaluators with criterion specific scores covering correctness, richness, coherence, cohesion, and task alignment enriched with detailed feedback and error examples. We fine-tune open-source models, including RoBERTa-EusCrawl and Latxa 8B/70B, for scoring. We focused on correctness criteria for the explanation generation, adapting Latxa to correctly predict both, scores and explanations. Our experiments show that encoder models remain highly reliable for AES, while supervised fine-tuning (SFT) of Latxa significantly enhances performance, surpassing state-of-the-art (SoTA) closed-source systems such as GPT-5 and Claude Sonnet 4.5 in scoring consistency and feedback quality. We also propose a novel evaluation methodology for assessing feedback generation, combining automatic consistency metrics with expert-based validation of extracted learner errors. Results demonstrate that the fine-tuned Latxa model produces criterion-aligned, pedagogically meaningful feedback and identifies a wider range of error types than proprietary models. This resource and benchmark establish a foundation for transparent, reproducible, and educationally grounded NLP research in low-resource languages such as Basque. The dataset, models and manual evalution results are available here: https://huggingface.co/collections/EkhiAzur/habe-hitz-c1
%R 10.63317/2vf49six8jhv
%U https://aclanthology.org/2026.lrec-1.54/
%U https://doi.org/10.63317/2vf49six8jhv
%P 735-746

Markdown (Informal)

[Automatic Essay Scoring and Feedback Generation in Basque Language Learning](https://aclanthology.org/2026.lrec-1.54/) (Azurmendi et al., LREC 2026)

• Automatic Essay Scoring and Feedback Generation in Basque Language Learning (Azurmendi et al., LREC 2026)

ACL

• Ekhi Azurmendi, Xabier Arregi, and Oier Lopez de Lacalle. 2026. Automatic Essay Scoring and Feedback Generation in Basque Language Learning. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 735–746, Palma de Mallorca, Spain. ELRA Language Resource Association.