文本到图像生成模型如何理解伦理自然语言干预？
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
摘要：
文本到图像生成模型在基于自然语言描述生成高质量图像方面取得了前所未有的成功。然而，它表明，这些模型往往有利于特定的社会群体时，提示与中性文本描述（例如，“一张律师的照片”。继Zhao等人（2021）之后，我们研究了在添加支持公平判断的伦理干预（例如，“如果所有人都可以成为律师，而不论其性别”）。为此，我们引入了一个道德自然语言干预文本到图像生成（ENTIGEN）基准数据集，以评估在三个社会轴-性别，肤色和文化的道德干预条件下的图像生成的变化。通过ENTIGEN框架，我们发现minDALL.E，DALL.E-mini和Stable Diffusion的生成覆盖了不同的社会群体，同时保持了图像质量。初步研究表明，在道德干预措施中的性别偏见背景下，模型预测的巨大变化是由某些短语引发的，例如“无论性别如何”。我们在https://github.com/Hritikbansal/entigen_emnlp上发布代码和注释数据。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
