arXiv Open Access 2025

Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations

Shaina Raza Maximus Powers Partha Pratim Saha Mahveen Raza Rizwan Qureshi
Lihat Sumber

Abstrak

Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evaluation task and introduce a pilot benchmark of occupational portrayals spanning five socially salient roles (CEO, Nurse, Software Engineer, Teacher, Athlete). Using five state-of-the-art models: closed-source (DALLE 3, Gemini Imagen 4.0) and open-source (FLUX.1-dev, Stable Diffusion XL Turbo, Grok-2 Image), we compare neutral baseline prompts against fairness-aware controlled prompts designed to encourage demographic diversity. All outputs are annotated for gender (male, female) and race (Asian, Black, White), enabling structured distributional analysis. Results show that prompting can substantially shift demographic representations, but with highly model-specific effects: some systems diversify effectively, others overcorrect into unrealistic uniformity, and some show little responsiveness. These findings highlight both the promise and the limitations of prompting as a fairness intervention, underscoring the need for complementary model-level strategies. We release all code and data for transparency and reproducibility https://github.com/maximus-powers/img-gen-bias-analysis.

Topik & Kata Kunci

Penulis (5)

S

Shaina Raza

M

Maximus Powers

P

Partha Pratim Saha

M

Mahveen Raza

R

Rizwan Qureshi

Format Sitasi

Raza, S., Powers, M., Saha, P.P., Raza, M., Qureshi, R. (2025). Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations. https://arxiv.org/abs/2509.00849

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓