Text-to-image generative models have achieved unprecedented success in generating high-quality images based on natural language descriptions. However, it is shown that these models 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 intervention 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 ENTIGEN framework, we find that the generations from minDALL.E, DALL.E-mini and Stable Diffusion cover diverse social groups while preserving the image quality. Preliminary studies indicate that a large change in the model predictions 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.
翻译:以自然语言描述为基础制作高质量图像的文字到模拟基因模型取得了前所未有的成功。然而,事实证明,这些模型在以中性文字描述(例如“律师的照片”)的提示下倾向于偏向特定社会群体。在赵等人(2021年)之后,我们在增加支持公平判断的道德干预(例如“如果所有个人都能成为律师,而不论其性别为何”)时,在输入提示中,对产生的图像的多样性进行了研究。为此,我们在文本到图像GEN(ENTIGEN)中引入了道德的“语言干预”基准数据集,以评价以性别、肤色和文化这三个社会轴心的道德干预为条件的几代形象变化。我们通过ENTIGEN框架发现,来自mol.E、DAL.E.Mini和Stable Difludifluction的几代人在维护图像质量的同时覆盖了不同的社会群体。我们的初步研究显示,模型预测的重大变化是由在httpsurgisional_brbrental-deality 代码中的某些短语引发的。我们通过在httpbabrental descrimalmentalmentalmentalismations.