发表机构
East China Normal University; National University of Singapore（华东师范大学; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对生成式AI教育视频缺乏教学结构的问题，提出PIVOT框架，将教学法融入生成流程，通过故事板引导、代码生成和验证、评估补救，在四个STEM领域验证了其教学有效性。
AI 中文摘要
生成式人工智能使得教育视频的大规模生产成为可能，但当前系统主要侧重于生成视觉上连贯的内容，而非支持学习。因此，生成的视频往往缺乏明确的教学结构、可靠的质量控制，以及评估学习者理解或解决误解的机制。在这项工作中，我们引入了PIVOT（教学法引导的教学视频辅导），一个通过以学习为中心的教学支持来促进STEM学习的生成式视频辅导框架。受传统教学工作流程的启发，我们的框架将教学法整合到整个生成流程中：首先，它利用教学原则指导故事板生成；然后，通过以代码为中心的生成和教学验证机制，产生经过验证的多模态视频；最后，将视频与评估和针对误解的补救措施相连接。在四个STEM领域的实验和专家评估表明，我们的框架能够生成具有教学对齐内容、清晰且引人入胜的呈现、连贯的教学流程以及被认为对学习有效的教育视频。这些发现提出了一个以人为中心的教育内容生成视角：生成系统不仅应通过其产生的内容来评估和设计，还应通过其如何支持教学实践、学习者理解和纠正性反馈来评估和设计。
英文摘要
Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than supporting learning. As a result, generated videos often lack explicit pedagogical structure, reliable quality control, and mechanisms for assessing learner understanding or addressing misconceptions. In this work, we introduce PIVOT (Pedagogy-guided Instructional VideO Tutoring), a generative video tutoring framework for STEM learning via learning-centered instructional support.1 Inspired by conventional teaching workflows, our framework integrates pedagogy into the full generation pipeline: it first uses instructional principles to guide storyboard generation, then produces verified multimodal videos through code-centric generation and a pedagogical verification harness, and finally connects videos with assessment and misconception-aware remediation. Experiments and expert evaluations across four STEM domains show that our framework produces educational videos with pedagogically aligned content, clear and engaging presentation, coherent instructional flow, and perceived effectiveness for learning. These findings suggest a human-centered perspective on educational content generation: generative systems should be evaluated and designed not only by what they produce, but also by how they support teaching practices, learner understanding, and corrective feedback.
Commentsaccepted to EMNLP 2026, code available at GitHub
