Sora视频生成模型存在性别偏见，易将特定性别与刻板角色关联。
Gender Bias in Text-to-Video Generation Models: A case study of Sora
- 用中性与刻板提示测试，分析生成视频中的性别分布。
- 模型显著倾向将男性与科技、女性与家务等角色绑定。
- 适合关注AI伦理、内容安全的研究者与从业者参考。
文本到视频生成模型的兴起彻底改变了内容创作方式，能够从文本提示生成高质量视频。然而，这类模型中固有的偏见引发了广泛关注，尤其是性别表现方面。本研究针对OpenAI的前沿文本到视频生成模型Sora，探讨其是否存在性别偏见。通过分析一系列性别中性及刻板印象提示所生成的视频，结果表明，Sora明显倾向于将特定性别与刻板行为和职业关联，反映出其训练数据中嵌入的社会偏见。
原文摘要 · Abstract (English)
The advent of text-to-video generation models has revolutionized content creation as it produces high-quality videos from textual prompts. However, concerns regarding inherent biases in such models have prompted scrutiny, particularly regarding gender representation. Our study investigates the presence of gender bias in OpenAI's Sora, a state-of-the-art text-to-video generation model. We uncover significant evidence of bias by analyzing the generated videos from a diverse set of gender-neutral and stereotypical prompts. The results indicate that Sora disproportionately associates specific genders with stereotypical behaviors and professions, which reflects societal prejudices embedded in its training data.
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。