@inproceedings{muller-eberstein-etal-2025-dakultur,
title = "{D}a{K}ultur: Evaluating the Cultural Awareness of Language Models for {D}anish with Native Speakers",
author = {M{\"u}ller-Eberstein, Max and
Zhang, Mike and
Bassignana, Elisa and
Trolle, Peter Brunsgaard and
Goot, Rob Van Der},
editor = "Prabhakaran, Vinodkumar and
Dev, Sunipa and
Benotti, Luciana and
Hershcovich, Daniel and
Cao, Yong and
Zhou, Li and
Cabello, Laura and
Adebara, Ife",
booktitle = "Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.c3nlp-1.5/",
doi = "10.18653/v1/2025.c3nlp-1.5",
pages = "50--58",
ISBN = "979-8-89176-237-4",
abstract = "Large Language Models (LLMs) have seen widespread societal adoption. However, while they are able to interact with users in languages beyond English, they have been shown to lack cultural awareness, providing anglocentric or inappropriate responses for underrepresented language communities. To investigate this gap and disentangle linguistic versus cultural proficiency, we conduct the first cultural evaluation study for the mid-resource language of Danish, in which native speakers prompt different models to solve tasks requiring cultural awareness. Our analysis of the resulting 1,038 interactions from 63 demographically diverse participants highlights open challenges to cultural adaptation: Particularly, how currently employed automatically translated data are insufficient to train or measure cultural adaptation, and how training on native-speaker data can more than double response acceptance rates. We release our study data as DaKultur - the first native Danish cultural awareness dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muller-eberstein-etal-2025-dakultur">
<titleInfo>
<title>DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Müller-Eberstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Bassignana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="given">Brunsgaard</namePart>
<namePart type="family">Trolle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="given">Van</namePart>
<namePart type="given">Der</namePart>
<namePart type="family">Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Cabello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ife</namePart>
<namePart type="family">Adebara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-237-4</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have seen widespread societal adoption. However, while they are able to interact with users in languages beyond English, they have been shown to lack cultural awareness, providing anglocentric or inappropriate responses for underrepresented language communities. To investigate this gap and disentangle linguistic versus cultural proficiency, we conduct the first cultural evaluation study for the mid-resource language of Danish, in which native speakers prompt different models to solve tasks requiring cultural awareness. Our analysis of the resulting 1,038 interactions from 63 demographically diverse participants highlights open challenges to cultural adaptation: Particularly, how currently employed automatically translated data are insufficient to train or measure cultural adaptation, and how training on native-speaker data can more than double response acceptance rates. We release our study data as DaKultur - the first native Danish cultural awareness dataset.</abstract>
<identifier type="citekey">muller-eberstein-etal-2025-dakultur</identifier>
<identifier type="doi">10.18653/v1/2025.c3nlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2025.c3nlp-1.5/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>50</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
%A Müller-Eberstein, Max
%A Zhang, Mike
%A Bassignana, Elisa
%A Trolle, Peter Brunsgaard
%A Goot, Rob Van Der
%Y Prabhakaran, Vinodkumar
%Y Dev, Sunipa
%Y Benotti, Luciana
%Y Hershcovich, Daniel
%Y Cao, Yong
%Y Zhou, Li
%Y Cabello, Laura
%Y Adebara, Ife
%S Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-237-4
%F muller-eberstein-etal-2025-dakultur
%X Large Language Models (LLMs) have seen widespread societal adoption. However, while they are able to interact with users in languages beyond English, they have been shown to lack cultural awareness, providing anglocentric or inappropriate responses for underrepresented language communities. To investigate this gap and disentangle linguistic versus cultural proficiency, we conduct the first cultural evaluation study for the mid-resource language of Danish, in which native speakers prompt different models to solve tasks requiring cultural awareness. Our analysis of the resulting 1,038 interactions from 63 demographically diverse participants highlights open challenges to cultural adaptation: Particularly, how currently employed automatically translated data are insufficient to train or measure cultural adaptation, and how training on native-speaker data can more than double response acceptance rates. We release our study data as DaKultur - the first native Danish cultural awareness dataset.
%R 10.18653/v1/2025.c3nlp-1.5
%U https://aclanthology.org/2025.c3nlp-1.5/
%U https://doi.org/10.18653/v1/2025.c3nlp-1.5
%P 50-58
Markdown (Informal)
[DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers](https://aclanthology.org/2025.c3nlp-1.5/) (Müller-Eberstein et al., C3NLP 2025)
ACL