Ahmad D. Suleiman, Daqing Hou, Maliha Noushin Raida (2026) — arXiv preprint.
Introduces 'design problems' (DPs): concise, scenario-based prompts that require applying knowledge in transfer contexts, generated with LLMs to assess higher-order thinking (HOT) in project-based learning. Traditional PjBL assessments often fail to capture HOT, especially transfer; DPs target that gap.
Bridges generative-ai generation with formative-assessment and project-based-learning, linking to scaffolding of complex tasks and higher-ed/cs-education contexts. It contributes a concrete method for scaling HOT assessment and informs ai-generated-content used for evaluation rather than just content delivery.
Related Pages
- project-based-learning — PjBL assessment context
- generative-ai — LLM-generated problems
- formative-assessment — HOT assessment method
- scaffolding — Scaffolding complex tasks
- higher-ed — Higher-ed computing
- cs-education — Computing education