@inproceedings{regneri-etal-2026-artful,
title = "Artful Writing, Authentic Emotions: Distinguishing Human-Written from {LLM}-Generated Metaphors by Annotation and Classification",
author = "Regneri, Michaela and
Aghajari, Nooshin and
Kroedel, Thomas",
editor = "Egg, Markus and
Kordoni, Valia",
booktitle = "Proceedings of Learning Non-Literal Expressions with Small Data @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nonliteral-1.6/",
doi = "10.63317/2q6dt9in7fm5",
pages = "51--76",
abstract = "We analyze differences between human-written and automatically generated metaphors. Using two syntactically standardized datasets containing novel metaphors from poetry and science communication, we generate new figurative expressions with LLMs that describe the same concepts as human-written texts. Using crowdsourcing, we conduct extensive annotation across multiple dimensions (e.g., writing quality and creativity) and ask annotators to judge whether the metaphor was generated automatically. For the poetry set, we also asked annotators for the emotions conveyed by the metaphor. We find that, consistent with prior work, the authorship of scientific metaphors is difficult to determine. However, our results reveal that human-written poetic metaphors stand out by their capacity to convey emotion. We also analyze which types of metaphors are merely perceived as human. Finally, we show that, while human annotators cannot distinguish human from machine metaphors, automated approaches achieve high accuracy in identifying human writers, which suggests substantial differences in text structure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="regneri-etal-2026-artful">
<titleInfo>
<title>Artful Writing, Authentic Emotions: Distinguishing Human-Written from LLM-Generated Metaphors by Annotation and Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michaela</namePart>
<namePart type="family">Regneri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nooshin</namePart>
<namePart type="family">Aghajari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Kroedel</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 Learning Non-Literal Expressions with Small Data @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Egg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valia</namePart>
<namePart type="family">Kordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We analyze differences between human-written and automatically generated metaphors. Using two syntactically standardized datasets containing novel metaphors from poetry and science communication, we generate new figurative expressions with LLMs that describe the same concepts as human-written texts. Using crowdsourcing, we conduct extensive annotation across multiple dimensions (e.g., writing quality and creativity) and ask annotators to judge whether the metaphor was generated automatically. For the poetry set, we also asked annotators for the emotions conveyed by the metaphor. We find that, consistent with prior work, the authorship of scientific metaphors is difficult to determine. However, our results reveal that human-written poetic metaphors stand out by their capacity to convey emotion. We also analyze which types of metaphors are merely perceived as human. Finally, we show that, while human annotators cannot distinguish human from machine metaphors, automated approaches achieve high accuracy in identifying human writers, which suggests substantial differences in text structure.</abstract>
<identifier type="citekey">regneri-etal-2026-artful</identifier>
<identifier type="doi">10.63317/2q6dt9in7fm5</identifier>
<location>
<url>https://aclanthology.org/2026.nonliteral-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>51</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Artful Writing, Authentic Emotions: Distinguishing Human-Written from LLM-Generated Metaphors by Annotation and Classification
%A Regneri, Michaela
%A Aghajari, Nooshin
%A Kroedel, Thomas
%Y Egg, Markus
%Y Kordoni, Valia
%S Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F regneri-etal-2026-artful
%X We analyze differences between human-written and automatically generated metaphors. Using two syntactically standardized datasets containing novel metaphors from poetry and science communication, we generate new figurative expressions with LLMs that describe the same concepts as human-written texts. Using crowdsourcing, we conduct extensive annotation across multiple dimensions (e.g., writing quality and creativity) and ask annotators to judge whether the metaphor was generated automatically. For the poetry set, we also asked annotators for the emotions conveyed by the metaphor. We find that, consistent with prior work, the authorship of scientific metaphors is difficult to determine. However, our results reveal that human-written poetic metaphors stand out by their capacity to convey emotion. We also analyze which types of metaphors are merely perceived as human. Finally, we show that, while human annotators cannot distinguish human from machine metaphors, automated approaches achieve high accuracy in identifying human writers, which suggests substantial differences in text structure.
%R 10.63317/2q6dt9in7fm5
%U https://aclanthology.org/2026.nonliteral-1.6/
%U https://doi.org/10.63317/2q6dt9in7fm5
%P 51-76
Markdown (Informal)
[Artful Writing, Authentic Emotions: Distinguishing Human-Written from LLM-Generated Metaphors by Annotation and Classification](https://aclanthology.org/2026.nonliteral-1.6/) (Regneri et al., NonLiteral 2026)
ACL