mlsanityData to 13 Oct 2026

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias

arXiv 2501.09014 ↗First posted 15 Jan 2025cs.SE cs.AIcited by 2

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images generated by these models could reinforce societal biases already existing in specific contexts. In this paper, we focus on understanding if this is the case when one generates images related to various software engineering tasks. In fact, the Software Engineering (SE) community is not immune from gender and ethnicity disparities, which could be amplified by the use of these models. Hence, if used without consciousness, artificially generated images could reinforce these biases in the SE domain. Specifically, we perform an extensive empirical evaluation of the gender and ethnicity bias exposed by three versions of the Stable Diffusion (SD) model (a very popular open-source text-to-image model) - SD 2, SD XL, and SD 3 - towards SE tasks. We obtain 6,720 images by feeding each model with two sets of prompts describing different software-related tasks: one set includes the Software Engineer keyword, and one set does not include any specification of the person performing the task. Next, we evaluate the gender and ethnicity disparities in the generated images. Results show how all models are significantly biased towards male figures when representing software engineers. On the contrary, while SD 2 and SD XL are strongly biased towards White figures, SD 3 is slightly more biased towards Asian figures. Nevertheless, all models significantly under-represent Black and Arab figures, regardless of the prompt style used. The results of our analysis highlight severe concerns about adopting those models to generate content for SE tasks and open the field for future research on bias mitigation in this context.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 15 of its 32 references that are in the map. First posted on arXiv 15 Jan 2025.

Builds on

15 of 32 references.

References · 15

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,323
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,314
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,141
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,130
  6. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  7. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 226
  8. 2023Social Biases through the Text-to-Image Generation Lenscited by 127
  9. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  10. 2022Large-scale Text-to-Image Generation Models for Visual Artists' Creative Workscited by 61
  11. 2023Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AIcited by 19
  12. 2023She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Modelscited by 12
3 more
  1. 2024Understanding Fairness in Software Engineering: Insights from Stack Exchangecited by 3
  2. 2024GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generationcited by 3
  3. 2023Data-Driven Analysis of Gender Fairness in the Software Engineering Academic Landscapecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Modelscited by 0
  2. 2025"Draw me a curator" Examining the visual stereotyping of a cultural services profession by generative AIcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Stable Diffusion Exposed: Gender Bias from Prompt to Image
  2. 2023Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models
  3. 2024Bias in Generative AI
  4. 2024Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Models
  5. 2026Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations
  6. 2024Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models
  7. 2026BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models
  8. 2024New Job, New Gender? Measuring the Social Bias in Image Generation Models