@inproceedings{pedersen-etal-2025-evaluating,
title = "Evaluating {LLM}-Generated Explanations of Metaphors {--} A Culture-Sensitive Study of {Danish}",
author = "Pedersen, Bolette S. and
S{\o}rensen, Nathalie and
Nimb, Sanni and
Hansen, Dorte Haltrup and
Olsen, Sussi and
Al-Laith, Ali",
editor = "Johansson, Richard and
Stymne, Sara",
booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nodalida-1.51/",
pages = "470--479",
ISBN = "978-9908-53-109-0",
abstract = "In this study, we examine how well Danish culture-specific metaphors are explained by two of the best performing language models for Danish, namely ChatGPT and Llama. For comparison, the explana- tions are measured against how well cross- lingual (or `universal') metaphors are ex- plained by the models; referring here to metaphors that exist in Danish as well as across cultures and languages and in par- ticular in English. To perform our study, we compile a pilot dataset of 150 Danish metaphors and idioms divided tentatively by culture specificity. We prompt the two models and perform a careful qualitative evaluation of the explanations against a four-graded scale. Our studies show that both models are heavily biased towards English since they have much more suc- cess in explaining the metaphors that also exist in English than the culture-specific ones, relying presumably on erroneous transfer from English when dealing with the latter. In particular, the sentiment of the culture-specific metaphors seems to be often `lost in translation'. We further claim that this strong colouring towards English poses a serious problem in the era of LLMs with regards to developing and maintaining cultural and linguistic diver- sity in other languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedersen-etal-2025-evaluating">
<titleInfo>
<title>Evaluating LLM-Generated Explanations of Metaphors – A Culture-Sensitive Study of Danish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bolette</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="family">Sørensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanni</namePart>
<namePart type="family">Nimb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorte</namePart>
<namePart type="given">Haltrup</namePart>
<namePart type="family">Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sussi</namePart>
<namePart type="family">Olsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Laith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-109-0</identifier>
</relatedItem>
<abstract>In this study, we examine how well Danish culture-specific metaphors are explained by two of the best performing language models for Danish, namely ChatGPT and Llama. For comparison, the explana- tions are measured against how well cross- lingual (or ‘universal’) metaphors are ex- plained by the models; referring here to metaphors that exist in Danish as well as across cultures and languages and in par- ticular in English. To perform our study, we compile a pilot dataset of 150 Danish metaphors and idioms divided tentatively by culture specificity. We prompt the two models and perform a careful qualitative evaluation of the explanations against a four-graded scale. Our studies show that both models are heavily biased towards English since they have much more suc- cess in explaining the metaphors that also exist in English than the culture-specific ones, relying presumably on erroneous transfer from English when dealing with the latter. In particular, the sentiment of the culture-specific metaphors seems to be often ‘lost in translation’. We further claim that this strong colouring towards English poses a serious problem in the era of LLMs with regards to developing and maintaining cultural and linguistic diver- sity in other languages.</abstract>
<identifier type="citekey">pedersen-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.51/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>470</start>
<end>479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating LLM-Generated Explanations of Metaphors – A Culture-Sensitive Study of Danish
%A Pedersen, Bolette S.
%A Sørensen, Nathalie
%A Nimb, Sanni
%A Hansen, Dorte Haltrup
%A Olsen, Sussi
%A Al-Laith, Ali
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F pedersen-etal-2025-evaluating
%X In this study, we examine how well Danish culture-specific metaphors are explained by two of the best performing language models for Danish, namely ChatGPT and Llama. For comparison, the explana- tions are measured against how well cross- lingual (or ‘universal’) metaphors are ex- plained by the models; referring here to metaphors that exist in Danish as well as across cultures and languages and in par- ticular in English. To perform our study, we compile a pilot dataset of 150 Danish metaphors and idioms divided tentatively by culture specificity. We prompt the two models and perform a careful qualitative evaluation of the explanations against a four-graded scale. Our studies show that both models are heavily biased towards English since they have much more suc- cess in explaining the metaphors that also exist in English than the culture-specific ones, relying presumably on erroneous transfer from English when dealing with the latter. In particular, the sentiment of the culture-specific metaphors seems to be often ‘lost in translation’. We further claim that this strong colouring towards English poses a serious problem in the era of LLMs with regards to developing and maintaining cultural and linguistic diver- sity in other languages.
%U https://aclanthology.org/2025.nodalida-1.51/
%P 470-479
Markdown (Informal)
[Evaluating LLM-Generated Explanations of Metaphors – A Culture-Sensitive Study of Danish](https://aclanthology.org/2025.nodalida-1.51/) (Pedersen et al., NoDaLiDa 2025)
ACL