Predictive, scalable and interpretable knowledge tracing on structured domains

arXiv:2403.13179v1 Announce Type: new
Abstract: Intelligent tutoring systems optimize the selection and timing of learning materials to enhance understanding and long-term retention. This requires estimates of both the learner's progress (''knowledge tracing''; KT), and the prerequisite structure of the learning domain (''knowledge mapping''). While recent deep learning models achieve high KT accuracy, they do so at the expense of the interpretability of psychologically-inspired models. In this work, we present a solution to this trade-off. PSI-KT is a hierarchical generative approach …

abstract arxiv cs.cy cs.lg deep learning domain domains intelligent knowledge long-term mapping materials predictive progress retention scalable stat.ml systems tracing tutoring type understanding