Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI
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.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingSimilar Papers 제목 키워드 기반
Gender Differences, Smiling, and Economic Negotiation Outcomes
Research documents gender differences in nonverbal behavior and negotiation outcomes. Women tend to smile more often than men and men generally perform better in economic negotiation contexts. Among nonverbal behaviors, …
Are There Any Body-movement Differences between Women and Men When They Laugh?
Smiling differences between men and women have been studied in psychology. Women smile more than men although the expressiveness of women is not universally more across all facial actions. There are also body movement di…
Pose EstimationUnequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of inte…
Word EmbeddingsUnequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of inte…
Word EmbeddingsContext Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles
Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images…
Gender Prediction