# GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension

arXiv: https://arxiv.org/abs/2604.09923 · HTML: https://mlsanity.com/paper/2604.09923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 30 of 30)

- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?](https://mlsanity.com/paper/2210.15230/) (2022)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.01261/) (2023)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- ['Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://mlsanity.com/paper/2310.19981/) (2023)
- [Studying Bias in GANs through the Lens of Race](https://mlsanity.com/paper/2209.02836/) (2022)
- [ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems](https://mlsanity.com/paper/2409.01392/) (2024)
- [ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation](https://mlsanity.com/paper/2401.06310/) (2024)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [Quantifying Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.13053/) (2023)
- [New Job, New Gender? Measuring the Social Bias in Image Generation Models](https://mlsanity.com/paper/2401.00763/) (2024)
- [ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation](https://mlsanity.com/paper/2503.17671/) (2025)
- [Understanding the Impact of AI Generated Content on Social Media: The Pixiv Case](https://mlsanity.com/paper/2402.18463/) (2024)
- [Social Perception of Faces in a Vision-Language Model](https://mlsanity.com/paper/2408.14435/) (2024)
- [Uncovering Bias in Face Generation Models](https://mlsanity.com/paper/2302.11562/) (2023)
- [Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models](https://mlsanity.com/paper/2407.00138/) (2024)
- [The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects](https://mlsanity.com/paper/2402.11089/) (2024)
- [OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis](https://mlsanity.com/paper/2506.02891/) (2025)
- [Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity](https://mlsanity.com/paper/2508.17465/) (2025)
- [A Taxonomy of the Biases of the Images created by Generative Artificial Intelligence](https://mlsanity.com/paper/2407.01556/) (2024)
- [Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models](https://mlsanity.com/paper/2505.14160/) (2025)
- [Interactive Discovery and Exploration of Visual Bias in Generative Text-to-Image Models](https://mlsanity.com/paper/2504.19703/) (2025)
- [Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI](https://mlsanity.com/paper/2508.07183/) (2025)
- [Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation](https://mlsanity.com/paper/2602.00032/) (2026)
- [Neutral Prompts, Non-Neutral People: Quantifying Gender and Skin-Tone Bias in Gemini Flash 2.5 Image and GPT Image 1.5](https://mlsanity.com/paper/2602.12133/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) models, and their encoded biases, increasingly shape the visual media the public encounters. While researchers have produced a rich body of work on bias measurement, auditing, and mitigation in T2I systems, those methods largely target technical stakeholders, leaving a gap in public legibility. We introduce GLEaN (Generative Likeness Evaluation at N-Scale), a portrait-based explainability pipeline designed to make T2I model biases visually understandable to a broad audience. GLEaN comprises three stages: automated large-scale image generation from identity prompts, facial landmark-based filtering and spatial alignment, and median-pixel composition that distills a model's central tendency into a single representative portrait. The resulting composites require no statistical background to interpret; a viewer can see, at a glance, who a model 'imagines' when prompted with 'a doctor' versus a 'felon.' We demonstrate GLEaN on Stable Diffusion XL across 40 social and occupational identity prompts, producing composites that reproduce documented biases and surface new associations between skin tone and predicted emotion. We find in a between-subjects user study (N = 291) that GLEaN portraits communicate biases as effectively as conventional data tables, but require significantly less viewing time. Because the method relies solely on generated outputs, it can also be replicated on any black-box and closed-weight systems without access to model internals. GLEaN offers a scalable, model-agnostic approach to bias explainability, purpose-built for public comprehension, and is publicly available at https://github.com/cultureiolab/GLEaN.