Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategies (2501.08441v1)

Abstract: Note: This paper includes examples of potentially offensive content related to religious bias, presented solely for academic purposes. The widespread adoption of LLMs highlights the need for critical examinations of their inherent biases, particularly concerning religion. This study systematically investigates religious bias in both LLMs and text-to-image generation models, analyzing both open-source and closed-source systems. We construct approximately 400 unique, naturally occurring prompts to probe LLMs 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 LLMs continue to exhibit significant biases in both text and image generation tasks, emphasizing the urgent need to develop fairer LLMs to achieve global acceptability.