4 papers
Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deployments
Alexandra Neagu, Jeffrey T. H. Wong, Marcus Messer +2
A central pedagogical value evaluated in AI tutor benchmarks is scaffolding: guiding students through graduated steps toward a solution. Alignment and evaluation methods for embedd…
Ed API: Towards a Shared API for Education Microservices
Maximillan Sölch, Alexandra Neagu, Marcus Messer +5
Learning at scale often requires domain-specific automation such as assessment and feedback. An organization locked in to a general learning platform without these specialist autom…
"How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations
Alexandra Neagu, Marcus Messer, Peter Johnson +1
Providing scaffolding through educational chatbots built on Large Language Models (LLM) has potential risks and benefits that remain an open area of research. When students navigat…
How Consistent Are Humans When Grading Programming Assignments?
Marcus Messer, Neil C. C. Brown, Michael Kölling +1
Providing consistent summative assessment to students is important, as the grades they are awarded affect their progression through university and future career prospects. While sm…