MOSAIC combines frozen-LLM semantic embeddings with hierarchical consistency objectives to report up to 3.4% AUC gains on knowledge-tracing benchmarks including a new MOOC dataset.
arXiv preprint arXiv:2502.02945 (2025)
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
fields
cs.LG 2representative citing papers
MC-Dropout uncertainty in DKT, SAKT and AKT models allows targeted abstention that raises accuracy 2.3-3.0 points and captures 77-90% architecture-specific epistemic signal unexplained by IRT or psychometric factors.
citing papers explorer
-
MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignment
MOSAIC combines frozen-LLM semantic embeddings with hierarchical consistency objectives to report up to 3.4% AUC gains on knowledge-tracing benchmarks including a new MOOC dataset.
-
Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing
MC-Dropout uncertainty in DKT, SAKT and AKT models allows targeted abstention that raises accuracy 2.3-3.0 points and captures 77-90% architecture-specific epistemic signal unexplained by IRT or psychometric factors.