<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reimann-scheffler-2025-struggles">
    <titleInfo>
        <title>The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Reimann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatjana</namePart>
        <namePart type="family">Scheffler</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>Extended metaphor is the use of multiple metaphoric words that express the same domain mapping. Although it would provide valuable insight for computational metaphor processing, detecting extended metaphor has been rather neglected. We fill this gap by providing a series of zero- and few-shot experiments on the detection of all linguistic metaphors and specifically on extended metaphors with LLaMa and GPT models. We find that no model was able to achieve satisfactory performance on either task, and that LLaMa in particular showed problematic overgeneralization tendencies. Moreover, our error analysis showed that LLaMa is not sufficiently able to construct the domain mappings relevant for metaphor understanding.</abstract>
    <identifier type="citekey">reimann-scheffler-2025-struggles</identifier>
    <identifier type="doi">10.21248/jlcl.38.2025.287</identifier>
    <location>
        <url>https://aclanthology.org/2025.jlcl-2.6/</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>97</start>
            <end>109</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection
%A Reimann, Sebastian
%A Scheffler, Tatjana
%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 reimann-scheffler-2025-struggles
%X Extended metaphor is the use of multiple metaphoric words that express the same domain mapping. Although it would provide valuable insight for computational metaphor processing, detecting extended metaphor has been rather neglected. We fill this gap by providing a series of zero- and few-shot experiments on the detection of all linguistic metaphors and specifically on extended metaphors with LLaMa and GPT models. We find that no model was able to achieve satisfactory performance on either task, and that LLaMa in particular showed problematic overgeneralization tendencies. Moreover, our error analysis showed that LLaMa is not sufficiently able to construct the domain mappings relevant for metaphor understanding.
%R 10.21248/jlcl.38.2025.287
%U https://aclanthology.org/2025.jlcl-2.6/
%U https://doi.org/10.21248/jlcl.38.2025.287
%P 97-109

Markdown (Informal)

[The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection](https://aclanthology.org/2025.jlcl-2.6/) (Reimann & Scheffler, JLCL 2025)

• The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection (Reimann & Scheffler, JLCL 2025)

ACL

• Sebastian Reimann and Tatjana Scheffler. 2025. The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection. Journal for Language Technology and Computational Linguistics, 38(2):97–109.