arxiv:2211.03759

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

Published on Nov 7, 2022

Upvote

Authors:

Federico Bianchi ,

Dan Jurafsky ,

Abstract

Image generation models amplify and perpetuate unpredictable and difficult-to-mitigate stereotypes in generated images.

AI-generated summary

Machine learning models are now able to convert user-written text descriptions into naturalistic images. These models are available to anyone online and are being used to generate millions of images a day. We investigate these models and find that they amplify dangerous and complex stereotypes. Moreover, we find that the amplified stereotypes are difficult to predict and not easily mitigated by users or model owners. The extent to which these image-generation models perpetuate and amplify stereotypes and their mass deployment is cause for serious concern.

View arXiv page View PDF Add to collection

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2211.03759 in a model README.md to link it from this page.

Datasets citing this paper 2

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2211.03759 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.