@inproceedings{singh-etal-2025-lets,
title = "Let{'}s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports",
author = "Singh, Punit Kumar and
Kumar, Nishant and
Ghosh, Akash and
Pasad, Kunal and
Soni, Khushi and
Jaishwal, Manisha and
Saha, Sriparna and
Alfarozi, Syukron Abu Ishaq and
Abagissa, Asres Temam and
Pasupa, Kitsuchart and
Yang, Haiqin and
Moreno, Jose G",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.769/",
doi = "10.18653/v1/2025.emnlp-main.769",
pages = "15194--15241",
ISBN = "979-8-89176-332-6",
abstract = "Language Models (LMs) are primarily evaluated on globally popular sports, often overlooking regional and indigenous sporting traditions. To address this gap, we introduce \textbf{ \textit{CultSportQA}}, a benchmark designed to assess LMs' understanding of traditional sports across 60 countries and 6 continents, encompassing four distinct cultural categories. The dataset features 33,000 multiple-choice questions (MCQs) across text and image modalities, categorized into primarily three key types: history-based, rule-based, and scenario-based. To evaluate model performance, we employ zero-shot, few-shot, and chain-of-thought (CoT) prompting across a diverse set of Large Language Models (LLMs), Small Language Models (SLMs), and Multimodal Large Language Models (MLMs). By providing a comprehensive multilingual and multicultural sports benchmark, \textbf{ \textit{CultSportQA}} establishes a new standard for assessing AI{'}s ability to understand and reason about traditional sports. The dataset will be publicly available, fostering research in culturally aware AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2025-lets">
<titleInfo>
<title>Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Punit</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishant</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Pasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manisha</namePart>
<namePart type="family">Jaishwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syukron</namePart>
<namePart type="given">Abu</namePart>
<namePart type="given">Ishaq</namePart>
<namePart type="family">Alfarozi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asres</namePart>
<namePart type="given">Temam</namePart>
<namePart type="family">Abagissa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kitsuchart</namePart>
<namePart type="family">Pasupa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiqin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Language Models (LMs) are primarily evaluated on globally popular sports, often overlooking regional and indigenous sporting traditions. To address this gap, we introduce CultSportQA, a benchmark designed to assess LMs’ understanding of traditional sports across 60 countries and 6 continents, encompassing four distinct cultural categories. The dataset features 33,000 multiple-choice questions (MCQs) across text and image modalities, categorized into primarily three key types: history-based, rule-based, and scenario-based. To evaluate model performance, we employ zero-shot, few-shot, and chain-of-thought (CoT) prompting across a diverse set of Large Language Models (LLMs), Small Language Models (SLMs), and Multimodal Large Language Models (MLMs). By providing a comprehensive multilingual and multicultural sports benchmark, CultSportQA establishes a new standard for assessing AI’s ability to understand and reason about traditional sports. The dataset will be publicly available, fostering research in culturally aware AI systems.</abstract>
<identifier type="citekey">singh-etal-2025-lets</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.769</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.769/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15194</start>
<end>15241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports
%A Singh, Punit Kumar
%A Kumar, Nishant
%A Ghosh, Akash
%A Pasad, Kunal
%A Soni, Khushi
%A Jaishwal, Manisha
%A Saha, Sriparna
%A Alfarozi, Syukron Abu Ishaq
%A Abagissa, Asres Temam
%A Pasupa, Kitsuchart
%A Yang, Haiqin
%A Moreno, Jose G.
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F singh-etal-2025-lets
%X Language Models (LMs) are primarily evaluated on globally popular sports, often overlooking regional and indigenous sporting traditions. To address this gap, we introduce CultSportQA, a benchmark designed to assess LMs’ understanding of traditional sports across 60 countries and 6 continents, encompassing four distinct cultural categories. The dataset features 33,000 multiple-choice questions (MCQs) across text and image modalities, categorized into primarily three key types: history-based, rule-based, and scenario-based. To evaluate model performance, we employ zero-shot, few-shot, and chain-of-thought (CoT) prompting across a diverse set of Large Language Models (LLMs), Small Language Models (SLMs), and Multimodal Large Language Models (MLMs). By providing a comprehensive multilingual and multicultural sports benchmark, CultSportQA establishes a new standard for assessing AI’s ability to understand and reason about traditional sports. The dataset will be publicly available, fostering research in culturally aware AI systems.
%R 10.18653/v1/2025.emnlp-main.769
%U https://aclanthology.org/2025.emnlp-main.769/
%U https://doi.org/10.18653/v1/2025.emnlp-main.769
%P 15194-15241
Markdown (Informal)
[Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports](https://aclanthology.org/2025.emnlp-main.769/) (Singh et al., EMNLP 2025)
ACL
- Punit Kumar Singh, Nishant Kumar, Akash Ghosh, Kunal Pasad, Khushi Soni, Manisha Jaishwal, Sriparna Saha, Syukron Abu Ishaq Alfarozi, Asres Temam Abagissa, Kitsuchart Pasupa, Haiqin Yang, and Jose G Moreno. 2025. Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sports. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15194–15241, Suzhou, China. Association for Computational Linguistics.