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

• URL: http://arxiv.org/abs/2509.00849v1
• Date: Sun, 31 Aug 2025 13:46:16 GMT
• Title: Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
• Authors: Shaina Raza, Maximus Powers, Partha Pratim Saha, Mahveen Raza, Rizwan Qureshi,
• Abstract summary: We frame representational societal bias assessment as an image curation and evaluation task.<n>Using five state-of-the-art models, we compare neutral baseline prompts against fairness-aware controlled prompts.<n>Results show that prompting can substantially shift demographic representations, but with highly model-specific effects.
• Score: 9.58968557546246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos [79.03150233804458]
  Real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution.<n>We propose a textbfface-only counterfactual evaluation paradigm<n>We generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed.
  arXiv  Detail & Related papers  (2026-01-11T14:35:06Z)
• FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models [10.857020427374506]
  We introduce FairImagen, a post-hoc debiasing framework that operates on prompt embeddings to mitigate societal biases.<n>Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.
  arXiv  Detail & Related papers  (2025-10-24T11:47:15Z)
• Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment [8.451522319478512]
  We introduce a news-image benchmark consisting of 1,343 image-question pairs drawn from diverse outlets.<n>We evaluate a range of state-of-the-art VLMs and employ a large language model (LLM) as judge, with human verification.<n>Our findings show that: (i) visual context systematically shifts model outputs in open-ended settings; (ii) bias prevalence varies across attributes and models, with particularly high risk for gender and occupation; and (iii) higher faithfulness does not necessarily correspond to lower bias.
  arXiv  Detail & Related papers  (2025-09-24T00:33:58Z)
• Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries [85.909363478929]
  In this study, we focus on 19 real-world statistics collected from authoritative sources.<n>We develop a checklist comprising objective and subjective queries to analyze behavior of large language models.<n>We propose metrics to assess factuality and fairness, and formally prove the inherent trade-off between these two aspects.
  arXiv  Detail & Related papers  (2025-02-09T10:54:11Z)
• DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model [20.915693552625502]
  We propose an inference-time process called DebiasPI for Debiasing-by-Prompt-Iteration.<n>DebiasPI enables the user to control the distributions of individuals' demographic attributes in image generation.
  arXiv  Detail & Related papers  (2025-01-28T23:17:20Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
  We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.<n>PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.<n>Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
  arXiv  Detail & Related papers  (2024-02-16T21:32:27Z)
• Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision [25.414154497482162]
  We demonstrate that diffusion models can be leveraged to create such a dataset. We benchmark several vision-language models on a multi-class occupation classification task. We find that images generated with non-Caucasian labels have a significantly higher occupation misclassification rate than images generated with Caucasian labels.
  arXiv  Detail & Related papers  (2023-11-25T19:40:13Z)
• Finetuning Text-to-Image Diffusion Models for Fairness [43.80733100304361]
  We frame fairness as a distributional alignment problem. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Our method supports diverse perspectives of fairness beyond absolute equality.
  arXiv  Detail & Related papers  (2023-11-11T05:40:54Z)
• Social Biases through the Text-to-Image Generation Lens [9.137275391251517]
  Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software. We take a multi-dimensional approach to studying and quantifying common social biases as reflected in the generated images. We present findings for two popular T2I models: DALLE-v2 and Stable Diffusion.
  arXiv  Detail & Related papers  (2023-03-30T05:29:13Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)
• DeAR: Debiasing Vision-Language Models with Additive Residuals [5.672132510411465]
  Large pre-trained vision-language models (VLMs) provide rich, adaptable image and text representations. These models suffer from societal biases owing to the skewed distribution of various identity groups in the training data. We present DeAR, a novel debiasing method that learns additive residual image representations to offset the original representations.
  arXiv  Detail & Related papers  (2023-03-18T14:57:43Z)
• How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? [67.97752431429865]
  We study the effect on the diversity of the generated images when adding ethical intervention. Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender'
  arXiv  Detail & Related papers  (2022-10-27T07:32:39Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.