@inproceedings{rystrom-etal-2025-multilingual,
title = "Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in {LLM}s",
author = "Rystr{\o}m, Jonathan Hvithamar and
Kirk, Hannah Rose and
Hale, Scott",
editor = "Przyby{\l}a, Piotr and
Shardlow, Matthew and
Colombatto, Clara and
Inie, Nanna",
booktitle = "Proceedings of Interdisciplinary Workshop on Observations of Misunderstood, Misguided and Malicious Use of Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ommm-1.9/",
pages = "74--85",
abstract = "Large Language Models (LLMs) are becoming increasingly capable across global languages. However, the ability to communicate across languages does not necessarily translate to appropriate cultural representations. A key concern is US-centric bias, where LLMs reflect US rather than local cultural values. We propose a novel methodology that compares LLM-generated response distributions against population-level opinion data from the World Value Survey across four languages (Danish, Dutch, English, and Portuguese). Using a rigorous linear mixed-effects regression framework, we compare three families of models: Google{'}s Gemma models (2B-27B parameters), AI2{'}s OLMo models (7B-32B parameters), and successive iterations of OpenAI{'}s turbo-series. Across the families of models, we find no consistent relationships between language capabilities and cultural alignment. While the Gemma models have a positive correlation between language capability and cultural alignment across all languages, the OpenAI and OLMo models are inconsistent. Our results demonstrate that achieving meaningful cultural alignment requires dedicated effort beyond improving general language capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rystrom-etal-2025-multilingual">
<titleInfo>
<title>Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">Hvithamar</namePart>
<namePart type="family">Rystrøm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Kirk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Hale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Interdisciplinary Workshop on Observations of Misunderstood, Misguided and Malicious Use of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Przybyła</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Colombatto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanna</namePart>
<namePart type="family">Inie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are becoming increasingly capable across global languages. However, the ability to communicate across languages does not necessarily translate to appropriate cultural representations. A key concern is US-centric bias, where LLMs reflect US rather than local cultural values. We propose a novel methodology that compares LLM-generated response distributions against population-level opinion data from the World Value Survey across four languages (Danish, Dutch, English, and Portuguese). Using a rigorous linear mixed-effects regression framework, we compare three families of models: Google’s Gemma models (2B-27B parameters), AI2’s OLMo models (7B-32B parameters), and successive iterations of OpenAI’s turbo-series. Across the families of models, we find no consistent relationships between language capabilities and cultural alignment. While the Gemma models have a positive correlation between language capability and cultural alignment across all languages, the OpenAI and OLMo models are inconsistent. Our results demonstrate that achieving meaningful cultural alignment requires dedicated effort beyond improving general language capabilities.</abstract>
<identifier type="citekey">rystrom-etal-2025-multilingual</identifier>
<location>
<url>https://aclanthology.org/2025.ommm-1.9/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>74</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
%A Rystrøm, Jonathan Hvithamar
%A Kirk, Hannah Rose
%A Hale, Scott
%Y Przybyła, Piotr
%Y Shardlow, Matthew
%Y Colombatto, Clara
%Y Inie, Nanna
%S Proceedings of Interdisciplinary Workshop on Observations of Misunderstood, Misguided and Malicious Use of Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F rystrom-etal-2025-multilingual
%X Large Language Models (LLMs) are becoming increasingly capable across global languages. However, the ability to communicate across languages does not necessarily translate to appropriate cultural representations. A key concern is US-centric bias, where LLMs reflect US rather than local cultural values. We propose a novel methodology that compares LLM-generated response distributions against population-level opinion data from the World Value Survey across four languages (Danish, Dutch, English, and Portuguese). Using a rigorous linear mixed-effects regression framework, we compare three families of models: Google’s Gemma models (2B-27B parameters), AI2’s OLMo models (7B-32B parameters), and successive iterations of OpenAI’s turbo-series. Across the families of models, we find no consistent relationships between language capabilities and cultural alignment. While the Gemma models have a positive correlation between language capability and cultural alignment across all languages, the OpenAI and OLMo models are inconsistent. Our results demonstrate that achieving meaningful cultural alignment requires dedicated effort beyond improving general language capabilities.
%U https://aclanthology.org/2025.ommm-1.9/
%P 74-85
Markdown (Informal)
[Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs](https://aclanthology.org/2025.ommm-1.9/) (Rystrøm et al., OMMM 2025)
ACL