<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yazdani-etal-2026-critical">
    <titleInfo>
        <title>A Critical Study of Automatic Evaluation in Sign Language Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shakib</namePart>
        <namePart type="family">Yazdani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yasser</namePart>
        <namePart type="family">HAMIDULLAH</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cristina</namePart>
        <namePart type="family">España-Bonet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eleftherios</namePart>
        <namePart type="family">Avramidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">van Genabith</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>Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably capture the quality of SLT outputs. To address this gap, we investigate the limitations of text-based SLT evaluation metrics by analyzing six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other hand. Specifically, we assess the consistency and robustness of these metrics under three controlled conditions: paraphrasing, hallucinations in model outputs, and variations in sentence length. Our analysis highlights the limitations of lexical overlap metrics and demonstrates that while LLM-based evaluators better capture semantic equivalence often missed by conventional metrics, they can also exhibit bias toward LLM-paraphrased translations. Moreover, although all metrics are able to detect hallucinations, BLEU tends to be overly sensitive, whereas BLEURT and LLM-based evaluators are comparatively lenient toward subtle cases. This motivates the need for multimodal evaluation frameworks that extend beyond text-based metrics to enable a more holistic assessment of SLT outputs.</abstract>
    <identifier type="citekey">yazdani-etal-2026-critical</identifier>
    <identifier type="doi">10.63317/4n2sooe4fb2i</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.749/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>9535</start>
            <end>9548</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Critical Study of Automatic Evaluation in Sign Language Translation
%A Yazdani, Shakib
%A HAMIDULLAH, Yasser
%A España-Bonet, Cristina
%A Avramidis, Eleftherios
%A van Genabith, Josef
%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 yazdani-etal-2026-critical
%X Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably capture the quality of SLT outputs. To address this gap, we investigate the limitations of text-based SLT evaluation metrics by analyzing six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other hand. Specifically, we assess the consistency and robustness of these metrics under three controlled conditions: paraphrasing, hallucinations in model outputs, and variations in sentence length. Our analysis highlights the limitations of lexical overlap metrics and demonstrates that while LLM-based evaluators better capture semantic equivalence often missed by conventional metrics, they can also exhibit bias toward LLM-paraphrased translations. Moreover, although all metrics are able to detect hallucinations, BLEU tends to be overly sensitive, whereas BLEURT and LLM-based evaluators are comparatively lenient toward subtle cases. This motivates the need for multimodal evaluation frameworks that extend beyond text-based metrics to enable a more holistic assessment of SLT outputs.
%R 10.63317/4n2sooe4fb2i
%U https://aclanthology.org/2026.lrec-1.749/
%U https://doi.org/10.63317/4n2sooe4fb2i
%P 9535-9548

Markdown (Informal)

[A Critical Study of Automatic Evaluation in Sign Language Translation](https://aclanthology.org/2026.lrec-1.749/) (Yazdani et al., LREC 2026)

• A Critical Study of Automatic Evaluation in Sign Language Translation (Yazdani et al., LREC 2026)

ACL

• Shakib Yazdani, Yasser HAMIDULLAH, Cristina España-Bonet, Eleftherios Avramidis, and Josef van Genabith. 2026. A Critical Study of Automatic Evaluation in Sign Language Translation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9535–9548, Palma de Mallorca, Spain. ELRA Language Resource Association.