Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems

The paper introduces Practical Integrated Cross-consistent Knowledge Tracing (PICKT), a model that incorporates multiple feature types to improve Knowledge Tracing robustness when new questions lack interaction history. It evaluates the impact of difficulty, textual, and knowledge‑map relational features, finding that difficulty is especially informative for hard questions, while fused text and map features help estimate unseen questions by leveraging similar ones seen during training. The study concludes that prioritizing feature annotation aligned with educational service characteristics is essential for maintaining robust diagnostics in Intelligent Tutoring Systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.