发表机构
College of Engineering, Northeastern University（东北大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究跨四代Stable Diffusion文生图模型在20个职业中的性别表现，发现76.4%图像为男性，女性占比被低估20-46个百分点，且偏差随模型更新未稳定改善，最新模型仍未实现性别均等。
AI 中文摘要
文生图生成模型在专业和创意环境中被广泛使用，然而，它们如何跨职业表现性别——以及更新模型是否更公平——在多个世代中仍知之甚少。我们评估了20个职业、5个提示模板和4个Stable Diffusion模型世代（SD 1.5、SD 2.1、SDXL、SD 3 Medium）中的性别表现，生成了8,000张图像，每个职业-模型单元格n=100（5个提示×20张图像），并使用DeepFace对所有图像进行分类。在这8,000张开源图像中，76.4%显示男性主体（95%置信区间[75.1%, 78.7%]，p < 2.2×10^-16，Benjamini-Hochberg校正）。更引人注目的是，历史上女性编码职业的图像中，57.6%显示男性主体（原始p = 3.43×10^-22，BH校正p = 1.71×10^-21）。本文报告的九个显著检验在10个检验中均通过BH校正。与美国劳工统计局劳动力数据相比，模型平均低估女性20-46个百分点，对于接近性别平衡的职业偏差尤其大：科学家（BLS中女性占48%，模型输出中男性占82-99%）和清洁工（BLS中女性占46%，模型输出中男性占80-92%）。模型世代并未稳步改进：偏差从SD 1.5到SDXL恶化，然后在SD 3 Medium中部分恢复。与GPT-image-1在五个职业上的初步比较表明，其偏差低于开源模型，尽管实际效果较小（Cramer's V = 0.080），且该比较是探索性的。没有模型实现性别均等。
英文摘要
Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether newer models are fairer -- remains poorly understood across multiple generations. We evaluate gender representation across 20 occupations, 5 prompt templates, and 4 Stable Diffusion model generations (SD 1.5, SD 2.1, SDXL, SD 3 Medium), generating 8,000 images with n = 100 per occupation-model cell (5 prompts x 20 images), and classifying all with DeepFace. Across the 8,000 open-source images, 76.4% show male subjects (95% CI [75.1%, 78.7%], p < 2.2 x 10^-16, Benjamini-Hochberg adjusted). More strikingly, 57.6% of images for historically female-coded occupations show male subjects (raw p = 3.43 x 10^-22, BH-adjusted p = 1.71 x 10^-21). All nine significant tests reported in this paper survive BH correction across 10 tests. When compared against U.S. Bureau of Labor Statistics workforce data, models underrepresent women by 20-46pp on average, with particularly large deviations for near gender-balanced occupations: scientist (48% female in BLS, 82-99% male in model outputs) and cleaner (46% female in BLS, 80-92% male in outputs). Model generations do not improve steadily: bias worsens from SD 1.5 to SDXL before partially recovering in SD 3 Medium. A preliminary comparison with GPT-image-1 on five occupations suggests lower bias than open-source models, though the practical effect is small (Cramer's V = 0.080) and the comparison is exploratory. No model achieves gender parity.
