# Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI

arXiv: https://arxiv.org/abs/2305.10566 · HTML: https://mlsanity.com/paper/2305.10566/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 60 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 7 of 7)

- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models](https://mlsanity.com/paper/2102.04130/) (2021)
- [Age and gender bias in pedestrian detection algorithms](https://mlsanity.com/paper/1906.10490/) (2019)
- [Female Librarians and Male Computer Programmers? Gender Bias in Occupational Images on Digital Media Platforms](https://mlsanity.com/paper/1912.05474/) (2019)

## Built on by (most cited first, 19 of 19)

- [Identifying and Improving Disability Bias in GPT-Based Resume Screening](https://mlsanity.com/paper/2402.01732/) (2024)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images](https://mlsanity.com/paper/2405.09426/) (2024)
- [Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black Individuals](https://mlsanity.com/paper/2412.09668/) (2024)
- [The AI Assessment Scale (AIAS) in action: A pilot implementation of GenAI supported assessment- A Preprint](https://mlsanity.com/paper/2403.14692/) (2024)
- [DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model](https://mlsanity.com/paper/2501.18642/) (2025)
- [Understanding Gender Bias in AI-Generated Product Descriptions](https://mlsanity.com/paper/2506.05390/) (2025)
- [How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias](https://mlsanity.com/paper/2501.09014/) (2025)
- [Refusal as Silence: Gendered Disparities in Vision-Language Model Responses](https://mlsanity.com/paper/2406.08222/) (2024)
- [AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation](https://mlsanity.com/paper/2406.12805/) (2024)
- [Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations](https://mlsanity.com/paper/2509.00849/) (2025)
- [Automated Evaluation of Gender Bias Across 13 Large Multimodal Models](https://mlsanity.com/paper/2509.07050/) (2025)
- [The Digital Mirror: Gender Bias and Occupational Stereotypes in AI-Generated Images](https://mlsanity.com/paper/2510.08628/) (2025)
- [Gender Artifacts from Art History to Text-to-Image Generation](https://mlsanity.com/paper/2606.05829/) (2026)
- [More Distinctively Black and Feminine Faces Lead to Increased Stereotyping in Vision-Language Models](https://mlsanity.com/paper/2407.06194/) (2024)
- [Visual Verity in AI-Generated Imagery: Computational Metrics and Human-Centric Analysis](https://mlsanity.com/paper/2408.12762/) (2024)
- [SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models](https://mlsanity.com/paper/2507.15663/) (2025)
- [Gender Bias in Generative AI-assisted Recruitment Processes](https://mlsanity.com/paper/2603.11736/) (2026)
- [Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies](https://mlsanity.com/paper/2604.16516/) (2026)

## Abstract (arXiv)

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.