Gender Bias in Text-to-Video Generation Models: A case study of Sora
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916560767025152 |
|---|---|
| author | Nadeem, Mohammad Sohail, Shahab Saquib Cambria, Erik Schuller, Björn W. Hussain, Amir |
| author_facet | Nadeem, Mohammad Sohail, Shahab Saquib Cambria, Erik Schuller, Björn W. Hussain, Amir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01987 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 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 Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society Machine Learning 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. |
| title | Gender Bias in Text-to-Video Generation Models: A case study of Sora |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2501.01987 |