Commonsense Reasoning in Arab Culture

TL;DR

This paper introduces ArabCulture, a culturally rich Arabic commonsense reasoning dataset, revealing that current large language models lack understanding of Arab cultural nuances and highlighting the need for culturally aware AI models.

Contribution

The paper presents ArabCulture, a new Arabic commonsense reasoning dataset built with native speaker input, capturing diverse Arab cultures and addressing biases in existing datasets.

Findings

Open-weight models underperform on ArabCulture tasks.

Model performance varies across different Arab regions.

Current models lack cultural understanding of Arab norms.

Abstract

Despite progress in Arabic large language models, such as Jais and AceGPT, their evaluation on commonsense reasoning has largely relied on machine-translated datasets, which lack cultural depth and may introduce Anglocentric biases. Commonsense reasoning is shaped by geographical and cultural contexts, and existing English datasets fail to capture the diversity of the Arab world. To address this, we introduce ArabCulture, a commonsense reasoning dataset in Modern Standard Arabic (MSA), covering cultures of 13 countries across the Gulf, Levant, North Africa, and the Nile Valley. The dataset was built from scratch by engaging native speakers to write and validate culturally relevant questions for their respective countries. ArabCulture spans 12 daily life domains with 54 fine-grained subtopics, reflecting various aspects of social norms, traditions, and everyday experiences. Zero-shot evaluations show that open-weight language models with up to 32B parameters struggle to comprehend diverse Arab cultures, with performance varying across regions. These findings highlight the need for more culturally aware models and datasets tailored to the Arabic-speaking world.