@inproceedings{fernandez-de-landa-etal-2026-llms,
title = "Why are all {LLM}s Obsessed with {J}apanese Culture? On the Hidden Cultural and Regional Biases of {LLM}s",
author = "Fernandez de Landa, Joseba and
Perez-Almendros, Carla and
Camacho-Collados, Jose",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1307/",
doi = "10.18653/2026.findings-emnlp.1307",
pages = "27628--27650",
ISBN = "979-8-89176-462-0",
abstract = "LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandez-de-landa-etal-2026-llms">
<titleInfo>
<title>Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseba</namePart>
<namePart type="family">Fernandez de Landa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Perez-Almendros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</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">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ.</abstract>
<identifier type="citekey">fernandez-de-landa-etal-2026-llms</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1307</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1307/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>27628</start>
<end>27650</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
%A Fernandez de Landa, Joseba
%A Perez-Almendros, Carla
%A Camacho-Collados, Jose
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F fernandez-de-landa-etal-2026-llms
%X LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ.
%R 10.18653/2026.findings-emnlp.1307
%U https://aclanthology.org/2026.findings-emnlp.1307/
%U https://doi.org/10.18653/2026.findings-emnlp.1307
%P 27628-27650
Markdown (Informal)
[Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs](https://aclanthology.org/2026.findings-emnlp.1307/) (Fernandez de Landa et al., Findings 2026)
ACL