Hartwig Grabowski, Michael Canz — cs.AI, cs.CV, cs.CY 📄 Full text (arXiv)
This paper identifies the didactic narrowing caused by fully digital e-assessment (overuse of closed question formats) and proposes a hybrid approach that retains paper-based, problem-oriented examination tasks while enabling semi-automated grading. The core technical innovation is applying vision-capable LLMs to recognize handwritten characters in structured answer fields under realistic exam conditions, combined with a two-pass validation principle and comparison against a solution key to reduce misclassifications. The approach addresses organizational, technical, and legal constraints that become relevant in large student cohorts. This work connects automated-grading research to real-world assessment practice by acknowledging that fully digital assessment often degrades assessment quality, even as institutions push for scalability. The hybrid approach could inform formative-assessment redesign in large-enrollment STEM courses.
Related Pages
- knowledge-tracing-irt — Knowledge tracing models and IRT for student modeling
- intelligent-tutoring — AI tutoring systems and adaptive instruction
- learning-analytics — Data-driven analysis of learning processes
- ai-literacy — Understanding and evaluating AI tools
- student-modeling — Representing learner knowledge and behavior
- cs-education — Computing education research and pedagogy
- self-regulated-learning — Metacognitive strategies for independent learning
- formative-assessment — Ongoing assessment to inform instruction
- automated-grading — AI-assisted evaluation of student work
- scaffolding — Instructional support that fades with competence
- automated-formative-assessments-a-level-sciences — Automating the marking of handwritten mock exams enables much higher formative-assessment frequency
Citations
APA: Hartwig Grabowski, Michael Canz (2026). Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations. arXiv:2606.08855. cs.AI, cs.CV, cs.CY.