@inproceedings{karmim-etal-2026-leveraging,
title = "Leveraging {W}ikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to {L}atin {A}merica",
author = "Karmim, Yannis and
Pino, Renato and
Contreras, Hernan and
Lira, Hernan and
Cifuentes, Sebastian and
Escoffier, Simon and
Mart{\'i}, Luis and
Seddah, Djam{\'e} and
Barriere, Valentin",
editor = "Chen, Pinzhen and
Zouhar, Vil{\'e}m and
Hu, Hanxu and
Khanuja, Simran and
Zhu, Wenhao and
Haddow, Barry and
Birch, Alexandra and
Aji, Alham Fikri and
Sennrich, Rico and
Hooker, Sara",
booktitle = "Proceedings of the First Workshop on Multilingual Multicultural Evaluation",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mme-main.11/",
pages = "177--188",
ISBN = "979-8-89176-368-5",
abstract = "Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack of resources to detect biases in non-English languages, especially from Latin America (Latam), a continent containing various cultures, even though they share a common cultural ground.We propose to leverage the content of Wikipedia, the structure of the Wikidata knowledge graph, and expert knowledge from social science in order to create a dataset of Questions/Answers (Q/As) pairs, based on the different popular and social cultures of various Latin American countries. We create a database of around 23k questions and associated answers extracted from 23k Wikipedia articles, and transformed into a multiple-choice questions (MCQ) in Spanish and Portuguese, in turn translated to English. We use this MCQ to quantify the degree of knowledge of various LLMs and find out extit{(i)} a discrepancy in performances between the Latam countries, ones being easier than others for the majority of the models, extit{(ii)} that the models perform better in their original language, extit{(iii)} that Iberian Spanish culture is better known than Latam one. Our code, our results for reproducing the results, and all datasets by region will be available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karmim-etal-2026-leveraging">
<titleInfo>
<title>Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Karmim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renato</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hernan</namePart>
<namePart type="family">Contreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hernan</namePart>
<namePart type="family">Lira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Cifuentes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Escoffier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Martí</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Multilingual Multicultural Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pinzhen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vilém</namePart>
<namePart type="family">Zouhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanxu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simran</namePart>
<namePart type="family">Khanuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Hooker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-368-5</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack of resources to detect biases in non-English languages, especially from Latin America (Latam), a continent containing various cultures, even though they share a common cultural ground.We propose to leverage the content of Wikipedia, the structure of the Wikidata knowledge graph, and expert knowledge from social science in order to create a dataset of Questions/Answers (Q/As) pairs, based on the different popular and social cultures of various Latin American countries. We create a database of around 23k questions and associated answers extracted from 23k Wikipedia articles, and transformed into a multiple-choice questions (MCQ) in Spanish and Portuguese, in turn translated to English. We use this MCQ to quantify the degree of knowledge of various LLMs and find out extit(i) a discrepancy in performances between the Latam countries, ones being easier than others for the majority of the models, extit(ii) that the models perform better in their original language, extit(iii) that Iberian Spanish culture is better known than Latam one. Our code, our results for reproducing the results, and all datasets by region will be available.</abstract>
<identifier type="citekey">karmim-etal-2026-leveraging</identifier>
<location>
<url>https://aclanthology.org/2026.mme-main.11/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>177</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America
%A Karmim, Yannis
%A Pino, Renato
%A Contreras, Hernan
%A Lira, Hernan
%A Cifuentes, Sebastian
%A Escoffier, Simon
%A Martí, Luis
%A Seddah, Djamé
%A Barriere, Valentin
%Y Chen, Pinzhen
%Y Zouhar, Vilém
%Y Hu, Hanxu
%Y Khanuja, Simran
%Y Zhu, Wenhao
%Y Haddow, Barry
%Y Birch, Alexandra
%Y Aji, Alham Fikri
%Y Sennrich, Rico
%Y Hooker, Sara
%S Proceedings of the First Workshop on Multilingual Multicultural Evaluation
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-368-5
%F karmim-etal-2026-leveraging
%X Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack of resources to detect biases in non-English languages, especially from Latin America (Latam), a continent containing various cultures, even though they share a common cultural ground.We propose to leverage the content of Wikipedia, the structure of the Wikidata knowledge graph, and expert knowledge from social science in order to create a dataset of Questions/Answers (Q/As) pairs, based on the different popular and social cultures of various Latin American countries. We create a database of around 23k questions and associated answers extracted from 23k Wikipedia articles, and transformed into a multiple-choice questions (MCQ) in Spanish and Portuguese, in turn translated to English. We use this MCQ to quantify the degree of knowledge of various LLMs and find out extit(i) a discrepancy in performances between the Latam countries, ones being easier than others for the majority of the models, extit(ii) that the models perform better in their original language, extit(iii) that Iberian Spanish culture is better known than Latam one. Our code, our results for reproducing the results, and all datasets by region will be available.
%U https://aclanthology.org/2026.mme-main.11/
%P 177-188
Markdown (Informal)
[Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America](https://aclanthology.org/2026.mme-main.11/) (Karmim et al., MME 2026)
ACL
- Yannis Karmim, Renato Pino, Hernan Contreras, Hernan Lira, Sebastian Cifuentes, Simon Escoffier, Luis Martí, Djamé Seddah, and Valentin Barriere. 2026. Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America. In Proceedings of the First Workshop on Multilingual Multicultural Evaluation, pages 177–188, Rabat, Morocco. Association for Computational Linguistics.