Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a breakthrough of inference speed. Despite their rapid progress, human biases that manifest in the training examples, particularly with regard to common stereotypical biases, like gender and skin tone, still have been found in these generative models. In this work, we seek to measure more complex human biases exist in the task of text-to-image generations. Inspired by the well-known Implicit Association Test (IAT) from social psychology, we propose a novel Text-to-Image Association Test (T2IAT) framework that quantifies the implicit stereotypes between concepts and valence, and those in the images. We replicate the previously documented bias tests on generative models, including morally neutral tests on flowers and insects as well as demographic stereotypical tests on diverse social attributes. The results of these experiments demonstrate the presence of complex stereotypical behaviors in image generations.

翻译：警告：本文包含若干可能具有毒性、有害性或冒犯性的内容。近年来，文本到图像生成模型在生成图像方面取得了前所未有的成功伴随推理速度的突破。尽管这些模型快速进步，训练样本中显现的人类偏见——尤其是常见的刻板偏见，如性别和肤色——仍在这些生成模型中被发现。在本工作中，我们旨在测量文本到图像生成任务中存在的更复杂的人类偏见。受社会心理学中著名的内隐联想测试（IAT）启发，我们提出了一种新颖的文本到图像联想测试（T2IAT）框架，该框架量化了概念与效价之间以及图像中的隐式刻板印象。我们复制了先前记录的生成模型偏见测试，包括关于花朵和昆虫的道德中性测试，以及关于多种社会属性的人口统计刻板测试。这些实验的结果表明，图像生成中存在复杂的刻板行为。