As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly prevalent and seeing growing adoption as commercial services, characterizing the social biases they exhibit is a necessary first step to lowering their risk of discriminatory outcomes. This evaluation, however, is made more difficult by the synthetic nature of these systems' outputs: common definitions of diversity are grounded in social categories of people living in the world, whereas the artificial depictions of fictive humans created by these systems have no inherent gender or ethnicity. To address this need, we propose a new method for exploring the social biases in TTI systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts, and comparing it to the variation engendered by spanning different professions. This allows us to (1) identify specific bias trends, (2) provide targeted scores to directly compare models in terms of diversity and representation, and (3) jointly model interdependent social variables to support a multidimensional analysis. We leverage this method to analyze images generated by 3 popular TTI systems (Dall-E 2, Stable Diffusion v 1.4 and 2) and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents. We also release the datasets and low-code interactive bias exploration platforms developed for this work, as well as the necessary tools to similarly evaluate additional TTI systems.

翻译：随着基于机器学习的文本到图像（TTI）系统日益普及，并越来越多地被用作商业服务，描述其表现出的社会偏见是降低其产生歧视性结果风险的必要第一步。然而，这些系统输出的合成性质使这一评估更加困难：多样性的一般定义基于现实世界中人类的社会类别，而这些系统创造的人工虚构人物描绘本身并无固有的性别或种族属性。为满足这一需求，我们提出了一种探索TTI系统中社会偏见的新方法。我们的方法依赖于通过枚举提示中的性别和种族标记来表征生成图像的变化，并将其与跨越不同职业所引起的变化进行比较。这使我们能够：（1）识别特定的偏见趋势；（2）提供有针对性的评分，以直接比较模型在多样性和表征方面的表现；（3）联合建模相互依赖的社会变量以支持多维分析。我们利用该方法分析了3个流行TTI系统（Dall-E 2、Stable Diffusion v 1.4和2）生成的图像，发现虽然它们的输出均与美国劳动力人口统计数据存在相关性，但也在不同程度上持续低估了边缘化身份的代表性。我们还发布了为此工作开发的数据集和低代码交互式偏见探索平台，以及用于类似评估其他TTI系统的必要工具。