@article{leitner-rehm-2025-exploring,
    title = "Exploring the Limits of {LLM}s for {G}erman Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets",
    author = "Leitner, Elena  and
      Rehm, Georg",
    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-2.1/",
    doi = "10.21248/jlcl.38.2025.277",
    pages = "1--12",
    abstract = {Large Language Models (LLMs) are highly capable, state-of-the-art technologies and widely used as text classifiers for various NLP tasks, including sentiment analysis, topic classification, legal document analysis, etc. In this paper, we present a systematic analysis of the performance of LLMs as text classifiers using five German datasets from social media across 13 different tasks. We investigate zero- (ZSC) and few-shot classification (FSC) approaches with multiple LLMs and provide a comparative analysis with fine-tuned models based on Llama-3.2, EuroLLM, Teuken and B{\"u}bleLM. We concentrate on investigating the limits of LLMs and on accurately describing our findings and overall challenges.}
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leitner-rehm-2025-exploring">
    <titleInfo>
        <title>Exploring the Limits of LLMs for German Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elena</namePart>
        <namePart type="family">Leitner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Georg</namePart>
        <namePart type="family">Rehm</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>Large Language Models (LLMs) are highly capable, state-of-the-art technologies and widely used as text classifiers for various NLP tasks, including sentiment analysis, topic classification, legal document analysis, etc. In this paper, we present a systematic analysis of the performance of LLMs as text classifiers using five German datasets from social media across 13 different tasks. We investigate zero- (ZSC) and few-shot classification (FSC) approaches with multiple LLMs and provide a comparative analysis with fine-tuned models based on Llama-3.2, EuroLLM, Teuken and BübleLM. We concentrate on investigating the limits of LLMs and on accurately describing our findings and overall challenges.</abstract>
    <identifier type="citekey">leitner-rehm-2025-exploring</identifier>
    <identifier type="doi">10.21248/jlcl.38.2025.277</identifier>
    <location>
        <url>https://aclanthology.org/2025.jlcl-2.1/</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>1</start>
            <end>12</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Exploring the Limits of LLMs for German Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets
%A Leitner, Elena
%A Rehm, Georg
%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 leitner-rehm-2025-exploring
%X Large Language Models (LLMs) are highly capable, state-of-the-art technologies and widely used as text classifiers for various NLP tasks, including sentiment analysis, topic classification, legal document analysis, etc. In this paper, we present a systematic analysis of the performance of LLMs as text classifiers using five German datasets from social media across 13 different tasks. We investigate zero- (ZSC) and few-shot classification (FSC) approaches with multiple LLMs and provide a comparative analysis with fine-tuned models based on Llama-3.2, EuroLLM, Teuken and BübleLM. We concentrate on investigating the limits of LLMs and on accurately describing our findings and overall challenges.
%R 10.21248/jlcl.38.2025.277
%U https://aclanthology.org/2025.jlcl-2.1/
%U https://doi.org/10.21248/jlcl.38.2025.277
%P 1-12
Markdown (Informal)

[Exploring the Limits of LLMs for German Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets](https://aclanthology.org/2025.jlcl-2.1/) (Leitner & Rehm, JLCL 2025)

ACL