Gender Bias in Text-to-Video Generation Models: A Case Study of Sora

Nadeem, Mohammad; Sohail, Shahab Saquib; Cambria, Erik; Schuller, Björn W.; Hussain, Amir

Abstract

The advent of text-to-video generation models has revolutionized content creation as it produces high-quality videos from textual prompts. However, concerns regarding inherent biases in such models have prompted scrutiny, particularly regarding gender representation. Our study investigates the presence of gender bias in OpenAI’s Sora, a state-of-the-art text-to-video generation model. We uncover significant evidence of bias by analyzing the generated videos from a diverse set of gender-neutral and stereotypical prompts. The results indicate that Sora disproportionately associates specific genders with stereotypical behaviors and professions, which reflects societal prejudices embedded in its training data.

Citation

Nadeem, M., Sohail, S. S., Cambria, E., Schuller, B. W., & Hussain, A. (2025). Gender Bias in Text-to-Video Generation Models: A Case Study of Sora. IEEE Intelligent Systems, 40(3), 10-15. https://doi.org/10.1109/mis.2025.3561475

• Journal Article Type: Article
• Online Publication Date: Jun 11, 2025
• Publication Date: 2025-06
• Deposit Date: Aug 7, 2025
• Journal: IEEE Intelligent Systems
• Print ISSN: 1541-1672
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 40
• Issue: 3
• Pages: 10-15
• DOI: https://doi.org/10.1109/mis.2025.3561475