Xiaozao Wang, Zhewei Wang, Hongyi Wen (2026) 📄 Full text (arXiv)
While llms now enable rapid generation of learning materials like ai-generated-content, evaluating the pedagogical quality of these materials remains an open challenge. This paper proposes an automated assessment framework for evaluating interactivity in AI-generated explorable explanations — dynamic, learner-driven content that students can manipulate to discover concepts. The framework addresses the gap between content generation speed and quality assurance, providing metrics for formative-assessment of learning designs. This connects to learning-analytics approaches for understanding how students engage with AI-produced educational content in higher-ed settings.
Related Pages
- automated-grading — Automated assessment approaches in computing education
- llm — Large language models and their applications
- k-12 — K-12 education context
- ai-literacy — AI literacy frameworks and assessment
- student-ai-interaction — How students interact with AI systems
- scaffolding — Instructional scaffolding techniques
- ai-generated-content — AI-produced educational materials
- learning-analytics — Data-driven analysis of learning behaviors
- formative-assessment — Formative assessment in AI-enhanced education
- active-learning — Active learning approaches
Citation
APA: Xiaozao Wang, Zhewei Wang, Hongyi Wen (2026). Evaluating Interactivity: Toward Automated Assessment of AI-Generated Explorable Explanations. arXiv:2606.31012.