English

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

Computers and Society 2023-02-15 v1 Computation and Language

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.

Keywords

Cite

@article{arxiv.2302.07159,
  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},
  journal= {arXiv preprint arXiv:2302.07159},
  year   = {2023}
}

Comments

Appearing in the AAAI 2023 Workshop on Creative AI Across Modalities

R2 v1 2026-06-28T08:39:59.359Z