@article{volkanovska-2025-study,
    title = "A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition",
    author = "Volkanovska, Elena",
    editor = "Tu, Ngoc Duyen Tanja  and
      Brunner, Annelen  and
      Lang, Christian",
    journal = "Journal for Language Technology and Computational Linguistics",
    volume = "38",
    number = "2",
    month = jul,
    year = "2025",
    publisher = "German Society for Computational Linguistics and Language Technology",
    url = "https://aclanthology.org/2025.jlcl-2.3/",
    doi = "10.21248/jlcl.38.2025.281",
    pages = "31--42",
    abstract = "This paper proposes an error classification framework for a comprehensive analysis of the output that large language models (LLMs) generate in a few-shot named entity recognition (NER) task in a specialised domain. The framework should be seen as an exploratory analysis complementary to established performance metrics for NER classifiers, such as F1 score, as it accounts for outcomes possible in a few-shot, LLM-based NER task. By categorising and assessing incorrect named entity predictions quantitatively, the paper shows how the proposed error classification could support a deeper cross-model and cross-prompt performance comparison, alongside a roadmap for a guided qualitative error analysis."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volkanovska-2025-study">
    <titleInfo>
        <title>A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elena</namePart>
        <namePart type="family">Volkanovska</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Journal for Language Technology and Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>German Society for Computational Linguistics and Language Technology</publisher>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>This paper proposes an error classification framework for a comprehensive analysis of the output that large language models (LLMs) generate in a few-shot named entity recognition (NER) task in a specialised domain. The framework should be seen as an exploratory analysis complementary to established performance metrics for NER classifiers, such as F1 score, as it accounts for outcomes possible in a few-shot, LLM-based NER task. By categorising and assessing incorrect named entity predictions quantitatively, the paper shows how the proposed error classification could support a deeper cross-model and cross-prompt performance comparison, alongside a roadmap for a guided qualitative error analysis.</abstract>
    <identifier type="citekey">volkanovska-2025-study</identifier>
    <identifier type="doi">10.21248/jlcl.38.2025.281</identifier>
    <location>
        <url>https://aclanthology.org/2025.jlcl-2.3/</url>
    </location>
    <part>
        <date>2025-07</date>
        <detail type="volume"><number>38</number></detail>
        <detail type="issue"><number>2</number></detail>
        <extent unit="page">
            <start>31</start>
            <end>42</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition
%A Volkanovska, Elena
%J Journal for Language Technology and Computational Linguistics
%D 2025
%8 July
%V 38
%N 2
%I German Society for Computational Linguistics and Language Technology
%F volkanovska-2025-study
%X This paper proposes an error classification framework for a comprehensive analysis of the output that large language models (LLMs) generate in a few-shot named entity recognition (NER) task in a specialised domain. The framework should be seen as an exploratory analysis complementary to established performance metrics for NER classifiers, such as F1 score, as it accounts for outcomes possible in a few-shot, LLM-based NER task. By categorising and assessing incorrect named entity predictions quantitatively, the paper shows how the proposed error classification could support a deeper cross-model and cross-prompt performance comparison, alongside a roadmap for a guided qualitative error analysis.
%R 10.21248/jlcl.38.2025.281
%U https://aclanthology.org/2025.jlcl-2.3/
%U https://doi.org/10.21248/jlcl.38.2025.281
%P 31-42
Markdown (Informal)

[A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition](https://aclanthology.org/2025.jlcl-2.3/) (Volkanovska, JLCL 2025)

ACL