AI生成图像强化白人审美，歧视非主流外貌特征。
Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models
- 构建美丑分类体系，测试文本到图像模型生成结果
- 86.5%图像肤色偏浅，74%显示年轻化，22%含不当内容
- 负面描述引发更多不适宜内容，加剧跨性别者污名化
社交媒体加剧了西方审美标准的传播，对女性和女孩造成负面自我形象，甚至引发身体畸形恐惧症。互联网内容日益由人工生成，令人担忧这些标准被进一步放大。本文研究生成式AI如何编码‘美’并抹除‘丑’，及其社会影响。我们构建了结构化的美丑分类体系，通过文本到图像及文本-语言模型到图像的双路径生成5984张图像，并邀请女性与非二元性别社交用户对其中1200张进行李克特量表评分。参与者评分高度一致。结果显示：86.5%生成图像人物肤色较浅，22%包含明确不当内容（尽管经过SFW训练），74%被归为更年轻年龄段。特别是非二元性别个体的图像被评价为更年轻且更性化，揭示了交叉性影响。值得注意的是，使用‘负面’或‘丑陋’外貌特征（如‘宽鼻’）提示时，无论性别，生成内容的非安全评级显著上升。本研究揭示了生成式AI中广泛存在的审美偏见——这些偏见正被开发者通过负向提示等机制主动强化。我们讨论其对社会的影响，包括数据流污染及对不符合主流审美的特征的系统性清除。
原文摘要 · Abstract (English)
Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。