Laurent Brisson, Maria Segarra, Grégory Smits (2026) — IMT Atlantique. arXiv preprint (cs.CY).
đź“„ Full text (arXiv)
Brisson, Segarra and Smits present a didactically-driven LLM teacher assistant for a university dimensional modeling (data warehousing) course. Unlike most educational chatbots that delegate pedagogical decisions implicitly to the LLM, their system makes content selection and didactic structuring explicit and traceable: tutoring strategy is encoded in an external didactic layer that the LLM executes, so tutoring behavior can be evaluated and reproduced. The design responds directly to the opacity critique raised in rethinking-scaffolding-llm-tutors and complements retrieval-grounded designs such as retrieval-augmented-tutoring-algorithm-kite and safety-layered tutors like eduguard-safe-rag-llm-tutor. As an instructor-facing pedagogical agent it sits alongside teachingcoach-chatbot-instructor-guidance, and its explicit didactic structuring exemplifies principled instructional-design applied to LLM tutoring in cs-education.
Related Pages
Citation
APA: Laurent Brisson, Maria Segarra, Grégory Smits (2026). A didactical-driven teacher assistant for a dimensional modeling course. arXiv:2607.22598.