# Bias in Generative AI

arXiv: https://arxiv.org/abs/2403.02726 · HTML: https://mlsanity.com/paper/2403.02726/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 23 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 1 of 1)

- [GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models](https://mlsanity.com/paper/2303.10130/) (2023)

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

- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [Transforming Teachers' Roles and Agencies in the Era of Generative AI: Perceptions, Acceptance, Knowledge, and Practices](https://mlsanity.com/paper/2410.03018/) (2024)
- [Variance reduction in output from generative AI](https://mlsanity.com/paper/2503.01033/) (2025)
- [LACONIC: A 3D Layout Adapter for Controllable Image Creation](https://mlsanity.com/paper/2507.03257/) (2025)
- [Towards Effective Discrimination Testing for Generative AI](https://mlsanity.com/paper/2412.21052/) (2024)
- [Interpersonal Theory of Suicide as a Lens to Examine Suicidal Ideation in Online Spaces](https://mlsanity.com/paper/2504.13277/) (2025)
- [FairSkin: Fair Diffusion for Skin Disease Image Generation](https://mlsanity.com/paper/2410.22551/) (2024)
- [Do LLMs have a Gender (Entropy) Bias?](https://mlsanity.com/paper/2505.20343/) (2025)
- [Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course](https://mlsanity.com/paper/2501.06461/) (2025)
- [CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models](https://mlsanity.com/paper/2508.20640/) (2025)
- [From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders](https://mlsanity.com/paper/2512.04843/) (2025)
- [HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing](https://mlsanity.com/paper/2605.24687/) (2026)
- [Attention Shift: Steering AI Away from Unsafe Content](https://mlsanity.com/paper/2410.04447/) (2024)
- [Trust, Experience, and Innovation: Key Factors Shaping American Attitudes About AI](https://mlsanity.com/paper/2503.05815/) (2025)
- [Using complex prompts to identify fine-grained biases in image generation through ChatGPT-4o](https://mlsanity.com/paper/2504.00388/) (2025)
- [The Rise of the Knowledge Sculptor: A New Archetype for Knowledge Work in the Age of Generative AI](https://mlsanity.com/paper/2510.07829/) (2025)
- [Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks](https://mlsanity.com/paper/2511.17393/) (2025)
- [Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training](https://mlsanity.com/paper/2602.16065/) (2026)
- [Practical Judgment, Virtue, and Intuition in the Use of Opaque AI-Enabled Systems](https://mlsanity.com/paper/2607.12755/) (2026)

## Abstract (arXiv)

This study analyzed images generated by three popular generative artificial intelligence (AI) tools - Midjourney, Stable Diffusion, and DALLE 2 - representing various occupations to investigate potential bias in AI generators. Our analysis revealed two overarching areas of concern in these AI generators, including (1) systematic gender and racial biases, and (2) subtle biases in facial expressions and appearances. Firstly, we found that all three AI generators exhibited bias against women and African Americans. Moreover, we found that the evident gender and racial biases uncovered in our analysis were even more pronounced than the status quo when compared to labor force statistics or Google images, intensifying the harmful biases we are actively striving to rectify in our society. Secondly, our study uncovered more nuanced prejudices in the portrayal of emotions and appearances. For example, women were depicted as younger with more smiles and happiness, while men were depicted as older with more neutral expressions and anger, posing a risk that generative AI models may unintentionally depict women as more submissive and less competent than men. Such nuanced biases, by their less overt nature, might be more problematic as they can permeate perceptions unconsciously and may be more difficult to rectify. Although the extent of bias varied depending on the model, the direction of bias remained consistent in both commercial and open-source AI generators. As these tools become commonplace, our study highlights the urgency to identify and mitigate various biases in generative AI, reinforcing the commitment to ensuring that AI technologies benefit all of humanity for a more inclusive future.