Broken Letters, Broken Narratives: A Case Study on Arabic Script in DALL-E 3

TL;DR

This paper critically examines how DALL-E 3 struggles to accurately generate calligraphic Arabic script, revealing biases and cultural misrepresentations rooted in under-representation and Orientalist perspectives.

Contribution

It provides a detailed case study highlighting the limitations and biases of AI in representing non-Western art forms, specifically Arabic calligraphy, and discusses broader cultural implications.

Findings

DALL-E 3 often produces inaccurate or distorted Arabic script.

Generated outputs reveal persistent biases and misrepresentations.

The study connects AI limitations to historical and cultural biases.

Abstract

Text-to-image generative AI systems exhibit significant limitations when engaging with under-represented domains, including non-Western art forms, often perpetuating biases and misrepresentations. We present a focused case study on the generative AI system DALL-E 3, examining its inability to properly represent calligraphic Arabic script, a culturally significant art form. Through a critical analysis of the generated outputs, we explore these limitations, emerging biases, and the broader implications in light of Edward Said's concept of Orientalism as well as historical examples of pseudo-Arabic. We discuss how misrepresentations persist in new technological contexts and what consequences they may have.