Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports
This addresses the problem of cultural bias in AI evaluations for researchers and developers, though it is incremental as it extends existing benchmarking approaches to a new domain.
The authors tackled the gap in evaluating language models on regional and indigenous sports by introducing CultSportQA, a benchmark with 33,000 multilingual and multicultural questions across 60 countries, and found that models performed poorly in zero-shot settings but improved with few-shot and chain-of-thought prompting.
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, each of which is categorized into 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.