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

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1358 - 1370 December 7-11, 2022 ©2022 Association for Computational Linguistics How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? Hritik Bansal∗ Da Yin∗ Masoud Monajatipoor Kai-Wei Chang Computer Science Department, University of California, Los Angeles {hbansal,da.yin,kwchang}@cs.ucla.edu, monajati@ucla.edu Abstract Text-to-image generative models have achieved unprecedented success in generating high- quality images based on natural language de- scriptions. However, it is shown that these mod- els tend to favor specific social groups when prompted with neutral text descriptions (e.g., ‘a photo of a lawyer’). Following Zhao et al. (2021), we study the effect on the diversity of the generated images when adding ethical inter- vention that supports equitable judgment (e.g., ‘if all individuals can be a lawyer irrespective of their gender’) in the input prompts. To this end, we introduce an Ethical NaTural Language Interventions in Text-to-Image GENeration (ENTIGEN) benchmark dataset to evaluate the change in image generations conditional on ethical interventions across three social axes – gender, skin color, and culture. Through ENTI- GEN framework, we find that the generations from minDALL·E, DALL·E-mini and Stable Diffusion cover diverse social groups while pre- serving the image quality. Preliminary studies indicate that a large change in the model pre- dictions is triggered by certain phrases such as ‘irrespective of gender’ in the context of gender bias in the ethical interventions. We release code and annotated data at https://github. com/Hritikbansal/entigen_emnlp. 1 Introduction Recent Text-to-Image generative models (Ramesh et al., 2021, 2022; Ding et al., 2021; Saharia et al., 2022; Nichol et al., 2021; Rombach et al., 2022) can synthesize high-quality photo-realistic images conditional on natural language text descriptions in a zero-shot fashion. For instance, they can gen- erate an image of ‘an armchair in the shape of an avocado’ which appears rarely in the real world. However, despite the unprecedented zero-shot abil- ities of the text-to-image generative models, recent experiments with small-scale instantiations (such ∗Equal Contribution Text-to-Image Generative Model a photo of a [profession] a photo of a [profession] if all individuals can be a [profession] irrespective of their [gender/skin color] a photo of a person wearing a [object] a photo of a person wearing a [object] if all individuals can wear a [object] irrespective of their [gender/skin color] Original Original with Ethical Intervention CLIP and Human Evaluation a photo of a bride a photo of a bride from diverse cultures Man Woman Gender Bias Light Dark Skin Color Bias Western Non- Western Cultural Bias Figure 1: We study the change in the model generations across various groups (man/woman, light-skinned/dark- skinned, Western/Non-Western) before and after adding ethical interventions (in purple) during text-to-image generation. We use CLIP and Human annotations to assign a social group to the model generations. We present a few output generations in Appendix Fig. 4-8. as minDALL·E) have shown that prompting the model with neutral texts (‘a photo of a lawyer’), devoid of any cues towards a social group, still gen- erates images that are …

Content truncated to 500 words