Generative Artificial Intelligence (AI) models like DALL·E 2 can interpret prompts and generate high-quality images that exhibit human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL·E 2 images spanning 153 occupations. We assessed potential bias amplification by benchmarking against the 2021 U.S. census data and Google Images. Our findings reveal that DALL·E 2 underrepresents women in male-dominated fields while overrepresenting them in female-dominated occupations. Additionally, DALL·E 2 images tend to depict more women than men with smiles and downward-pitching heads, particularly in female-dominated (versus male-dominated) occupations. Our algorithm auditing study demonstrates more pronounced representational and presentational biases in DALL·E 2 compared to Google Images and calls for feminist interventions to curtail the potential impacts of such biased AI-generated images on the media ecology.

中文翻译：

---

微笑的女性俯身：审核图像生成人工智能中的代表性和表现性性别偏见

DALL·E 2 等生成人工智能 (AI) 模型可以解释提示并生成展现人类创造力的高质量图像。尽管公众热情高涨，但对人工智能生成图像中潜在性别偏见的系统审核仍然很少。我们通过检查涵盖 153 个职业的 15,300 张 DALL·E 2 图像中两种职业性别偏见（代表性偏见和表象偏见）的普遍程度来解决这一差距。我们通过对 2021 年美国人口普查数据和 Google 图片进行基准评估来评估潜在的偏差放大。我们的研究结果表明，DALL·E 2 在男性主导领域中女性代表性不足，而在女性主导职业中女性代表性过高。此外，DALL·E 2 图像中微笑和低头的女性多于男性，尤其是在女性占主导地位（相对于男性占主导地位）的职业中。我们的算法审核研究表明，与 Google 图片相比，DALL·E 2 中存在更明显的代表性和表现性偏见，并呼吁女权主义干预措施，以减少这种有偏见的人工智能生成图像对媒体生态的潜在影响。