English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Text-to-image models take a sentence (i.e., prompt) and generate imagesassociated with this input prompt. These models have created award wining-art,videos, and even synthetic datasets. However, text-to-image (T2I) models cangenerate images that underrepresent minorities based on race and sex. Thispaper investigates which word in the input prompt is responsible for bias ingenerated images. We introduce a method for computing scores for each word inthe prompt; these scores represent its influence on biases in the model'soutput. Our method follows the principle of \emph{explaining by removing},leveraging masked language models to calculate the influence scores. We performexperiments on Stable Diffusion to demonstrate that our method identifies thereplication of societal stereotypes in generated images.

Word-Level Explanations for Analyzing Bias in Text-to-Image Models