MyCulture: Exploring Malaysia's Diverse Culture under Low-Resource Language Constraints

TL;DR

This paper introduces MyCulture, a benchmark for evaluating Malaysian cultural understanding in LLMs, addressing biases in low-resource languages with a novel open-ended question format and comprehensive bias analysis.

Contribution

We propose a new cultural benchmark with an open-ended format and theoretical insights, specifically targeting low-resource language challenges in LLM evaluation.

Findings

Significant disparities in model cultural comprehension.

Open-ended format improves fairness and discriminative power.

Bias analysis reveals structural and language biases in LLMs.

Abstract

Large Language Models (LLMs) often exhibit cultural biases due to training data dominated by high-resource languages like English and Chinese. This poses challenges for accurately representing and evaluating diverse cultural contexts, particularly in low-resource language settings. To address this, we introduce MyCulture, a benchmark designed to comprehensively evaluate LLMs on Malaysian culture across six pillars: arts, attire, customs, entertainment, food, and religion presented in Bahasa Melayu. Unlike conventional benchmarks, MyCulture employs a novel open-ended multiple-choice question format without predefined options, thereby reducing guessing and mitigating format bias. We provide a theoretical justification for the effectiveness of this open-ended structure in improving both fairness and discriminative power. Furthermore, we analyze structural bias by comparing model performance on structured versus free-form outputs, and assess language bias through multilingual prompt variations. Our evaluation across a range of regional and international LLMs reveals significant disparities in cultural comprehension, highlighting the urgent need for culturally grounded and linguistically inclusive benchmarks in the development and assessment of LLMs.