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

Isar Nejadgholi; Kathleen C. Fraser; Svetlana Kiritchenko

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.07159 v1 pith:PNU55ZPZ submitted 2023-02-14 cs.CY cs.CL

Kathleen C. Fraser , Svetlana Kiritchenko , Isar Nejadgholi This is my paper · ORCID

classification cs.CYcs.CL

keywords imagescontainfriendlygeneratedpersonportraitsocialsystems

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
cs.CV 2025-01 conditional novelty 7.0 of 10

Standard gender-bias detectors for text-to-image models deviate substantially from human-annotated bias, and a face-filtering plus CLIP pipeline measures bias more accurately.

Pith tools