A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?

Kathleen C. Fraser, Svetlana Kiritchenko, Isar Nejadgholi
2/14/2023
cs.CYcs.CL

No confident code implementation found for this paper.

Abstract

As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are visually under-specified, but contain salient social attributes (e.g., 'a portrait of a threatening person' versus 'a portrait of a friendly person'). Grounding our work in social cognition theory, we find that in many cases, images contain similar demographic biases to those reported in the stereotype literature. However, trends are inconsistent across different models and further investigation is warranted.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation

90% match1 repo72023

Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models

88% match2024

When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models

88% match2025

Uncovering Bias in Large Vision-Language Models with Counterfactuals

87% match2024

Social Biases through the Text-to-Image Generation Lens

86% match2023

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation

86% match2024

Cite this paper

@article{fraser2023friendly,
  title  = {A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?},
  author = {Kathleen C. Fraser and Svetlana Kiritchenko and Isar Nejadgholi},
  year   = {2023},
  eprint = {2302.07159},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.07159v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.07159.svg)](https://codeofpaper.com/paper/2302.07159)

Discussion