Principled Transformers for Predictive Performance in Knowledge Tracing

SAGE: A Synthetic Graph Framework for Personalized Student Knowledge-State Modeling

EKT-XAI: an integrated framework for scalable and explainable knowledge tracing with lightweight transformers

Knowledge tracing, which models the evolution of student knowledge from interaction sequences, is fundamental to adaptive learning systems, yet existing approaches struggle to achieve scalability, computational efficiency, and interpretability simultaneously. This paper presents EKT-XAI, an integrated framework addre...

From Answers to Policies: Efficient In-Context Learning System through Emulating Expert Investigation

A route to more efficient inference-time scaling is supported: PIHF-MCP develops reusable policies from a few examples that improve performance on unseen cases and across models.

Stable and Faithful Explanations for Knowledge Tracing

Knowledge tracing (KT) models predict student performance opaquely, limiting pedagogical action. This study contributes a validation protocol testing predictive competitiveness (RQ1), explanation stability (RQ2) and retraining-based faithfulness (RQ3) together. Thirteen behavioral features across five pedagogical theme...

DiffKT: a diffusion model for fine-grained knowledge tracing

DiffKT is proposed, a diffusion-based framework for fine-grained knowledge tracing that models learners’ knowledge states as probabilistic distributions rather than fixed point estimates, highlighting its effectiveness in modeling noisy and fine-grained learning behaviors.

AMDKT: An Interpretable Dual-Stream Transformer for Knowledge Tracing via Student Proficiency–Item Competency Matching (SPIM)

Knowledge tracing (KT) is a core technology in intelligent tutoring systems that predicts students’ future responses by analyzing their historical interaction sequences. Although existing deep learning-based KT models achieve high predictive accuracy, their “black-box” nature severely hinders practical deployment in ed...