AlDahoul Nouar, Rahwan Talal, Zaki Yasir
New York University, Abu Dhabi, UAE.
Sci Rep. 2025 Apr 25;15(1):14449. doi: 10.1038/s41598-025-99623-3.
Text-to-image generative AI models such as Stable Diffusion are used daily by millions worldwide. However, the extent to which these models exhibit racial and gender stereotypes is not yet fully understood. Here, we document significant biases in Stable Diffusion across six races, two genders, 32 professions, and eight attributes. Additionally, we examine the degree to which Stable Diffusion depicts individuals of the same race as being similar to one another. This analysis reveals significant racial homogenization, e.g., depicting nearly all Middle Eastern men as bearded, brown-skinned, and wearing traditional attire. We then propose debiasing solutions that allow users to specify the desired distributions of race and gender when generating images while minimizing racial homogenization. Finally, using a preregistered survey experiment, we find evidence that being presented with inclusive AI-generated faces reduces people's racial and gender biases, while being presented with non-inclusive ones increases such biases, regardless of whether the images are labeled as AI-generated. Taken together, our findings emphasize the need to address biases and stereotypes in text-to-image models.
诸如Stable Diffusion这样的文本到图像生成式人工智能模型，每天都被全球数百万人使用。然而，这些模型表现出种族和性别刻板印象的程度尚未得到充分了解。在这里，我们记录了Stable Diffusion在六个种族、两种性别、32种职业和八个属性方面存在的显著偏差。此外，我们还研究了Stable Diffusion将同一种族的个体描绘得彼此相似的程度。这一分析揭示了显著的种族同质化现象，例如，几乎将所有中东男性都描绘成留着胡须、棕色皮肤且穿着传统服装的形象。然后，我们提出了去偏解决方案，允许用户在生成图像时指定所需的种族和性别分布，同时尽量减少种族同质化。最后，通过一项预先注册的调查实验，我们发现有证据表明，展示包容性的人工智能生成的面孔会减少人们的种族和性别偏见，而展示非包容性的面孔则会增加这种偏见，无论这些图像是否被标记为人工智能生成的。综上所述，我们的研究结果强调了解决文本到图像模型中的偏见和刻板印象的必要性。
