用自动化方法检测AI生成教学内容中的偏见，提升审核公平性与效率。
Automated Bias Assessment in AI-Generated Educational Content Using CEAT Framework
- 结合上下文嵌入与提示工程，构建可检索增强的偏见评估框架。
- 人工与自动提取词汇相关性达 r=0.993，结果高度一致。
- 适合教育科技、AI伦理审查及内容安全团队使用。
生成式人工智能（GenAI）在教育内容创作中迅速发展，尤其在导师培训材料开发中应用广泛。然而，嵌入在生成内容中的性别、种族或国籍刻板印象等偏见引发重大伦理与教育问题。尽管GenAI使用日益普遍，针对教育材料中此类偏见的系统性检测与评估方法仍有限。本研究提出一种自动化偏见评估方法，将上下文嵌入关联测试（CEAT）与提示工程词提取法结合，嵌入检索增强生成框架中。该方法应用于AI生成的导师培训文本，结果显示自动与人工标注词集高度一致，皮尔逊相关系数 r = 0.993，表明评估结果可靠且稳定。该方法有效降低人为主观性，提升审计过程的公平性、可扩展性与可复现性。
原文摘要 · Abstract (English)
Recent advances in Generative Artificial Intelligence (GenAI) have transformed educational content creation, particularly in developing tutor training materials. However, biases embedded in AI-generated content--such as gender, racial, or national stereotypes--raise significant ethical and educational concerns. Despite the growing use of GenAI, systematic methods for detecting and evaluating such biases in educational materials remain limited. This study proposes an automated bias assessment approach that integrates the Contextualized Embedding Association Test with a prompt-engineered word extraction method within a Retrieval-Augmented Generation framework. We applied this method to AI-generated texts used in tutor training lessons. Results show a high alignment between the automated and manually curated word sets, with a Pearson correlation coefficient of r = 0.993, indicating reliable and consistent bias assessment. Our method reduces human subjectivity and enhances fairness, scalability, and reproducibility in auditing GenAI-produced educational content.
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。