Mathematics Isn't Culture-Free: Probing Cultural Gaps via Entity and Scenario Perturbations

TL;DR

This study reveals that large language models perform differently on math problems depending on cultural context, with reasoning abilities helping to mitigate cultural presentation gaps.

Contribution

The paper introduces culturally adapted variants of a math benchmark and evaluates model robustness to cultural differences in problem presentation.

Findings

Models perform best on US-centric problems.

Cultural adaptations reduce model performance.

Reasoning capabilities improve resilience to cultural shifts.

Abstract

Although mathematics is often considered culturally neutral, the way mathematical problems are presented can carry implicit cultural context. Existing benchmarks like GSM8K are predominantly rooted in Western norms, including names, currencies, and everyday scenarios. In this work, we create culturally adapted variants of the GSM8K test set for five regions Africa, India, China, Korea, and Japan using prompt-based transformations followed by manual verification. We evaluate six large language models (LLMs), ranging from 8B to 72B parameters, across five prompting strategies to assess their robustness to cultural variation in math problem presentation. Our findings reveal a consistent performance gap: models perform best on the original US-centric dataset and comparatively worse on culturally adapted versions. However, models with reasoning capabilities are more resilient to these shifts, suggesting that deeper reasoning helps bridge cultural presentation gaps in mathematical tasks