Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI
This addresses bias in AI-generated images, which could perpetuate stereotypes in media, but is incremental as it builds on existing auditing methods.
The study audited gender biases in DALL-E 2 by analyzing 15,300 images across 153 occupations, finding it underrepresents women in male-dominated fields and overrepresents them in female-dominated ones, with biases more pronounced than in Google Images.
Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL-E 2 images spanning 153 occupations, and assessed potential bias amplification by benchmarking against 2021 census labor statistics and Google Images. Our findings reveal that DALL-E 2 underrepresents women in male-dominated fields while overrepresenting them in female-dominated occupations. Additionally, DALL-E 2 images tend to depict more women than men with smiling faces and downward-pitching heads, particularly in female-dominated (vs. male-dominated) occupations. Our computational algorithm auditing study demonstrates more pronounced representational and presentational biases in DALL-E 2 compared to Google Images and calls for feminist interventions to prevent such bias-laden AI-generated images to feedback into the media ecology.