Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategies

TL;DR

This paper systematically investigates religious bias in language and text-to-image models, revealing significant biases and evaluating debiasing techniques to promote fairness in AI systems.

Contribution

It provides a comprehensive analysis of religious bias in multiple AI models, introduces a large set of prompts for bias detection, and assesses debiasing strategies for reducing such biases.

Findings

Language models exhibit significant religious biases.

Biases intersect with demographic factors like gender and nationality.

Debiasing prompts can mitigate some biases.

Abstract

Note: This paper includes examples of potentially offensive content related to religious bias, presented solely for academic purposes. The widespread adoption of language models highlights the need for critical examinations of their inherent biases, particularly concerning religion. This study systematically investigates religious bias in both language models and text-to-image generation models, analyzing both open-source and closed-source systems. We construct approximately 400 unique, naturally occurring prompts to probe language models for religious bias across diverse tasks, including mask filling, prompt completion, and image generation. Our experiments reveal concerning instances of underlying stereotypes and biases associated disproportionately with certain religions. Additionally, we explore cross-domain biases, examining how religious bias intersects with demographic factors such as gender, age, and nationality. This study further evaluates the effectiveness of targeted debiasing techniques by employing corrective prompts designed to mitigate the identified biases. Our findings demonstrate that language models continue to exhibit significant biases in both text and image generation tasks, emphasizing the urgent need to develop fairer language models to achieve global acceptability.