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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text-to-image generative models have achieved unprecedented success ingenerating high-quality images based on natural language descriptions. However,it is shown that these models tend to favor specific social groups whenprompted with neutral text descriptions (e.g., 'a photo of a lawyer').Following Zhao et al. (2021), we study the effect on the diversity of thegenerated images when adding ethical intervention that supports equitablejudgment (e.g., 'if all individuals can be a lawyer irrespective of theirgender') in the input prompts. To this end, we introduce an Ethical NaTuralLanguage Interventions in Text-to-Image GENeration (ENTIGEN) benchmark datasetto evaluate the change in image generations conditional on ethicalinterventions across three social axes -- gender, skin color, and culture.Through ENTIGEN framework, we find that the generations from minDALL.E,DALL.E-mini and Stable Diffusion cover diverse social groups while preservingthe image quality. Preliminary studies indicate that a large change in themodel predictions is triggered by certain phrases such as 'irrespective ofgender' in the context of gender bias in the ethical interventions. We releasecode and annotated data at https://github.com/Hritikbansal/entigen_emnlp.

How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?