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 themes were engineered from ASSISTments 2009 and 2012, with history features computed from temporally preceding interactions and current response latency retained only for retrospective analysis. ASSISTments 2009 was rebuilt: the uncorrected skill-builder release duplicates each multi-skill interaction across one row per skill, and because those rows share one correctness label, they leak it into preceding-interaction features. Rebuilding lowered model AUC and reordered the explanation results. An Extreme Gradient Boosting (XGBoost) model explained with Tree SHapley Additive exPlanations (TreeSHAP) was compared against four deep baselines (DKT, SAKT, AKT and SimpleKT) under an information-matched protocol giving the deep models the same behavioral signals and restricting XGBoost to what is derivable from the identifier-and-correctness stream they consume. XGBoost reached an area under the curve (AUC) of 0.777 on 2012 and 0.786 on rebuilt 2009, with prediction-time AUCs of 0.771 and 0.775, respectively, after excluding current response latency; restricted to the baselines'information it performed as they did (0.697 against 0.700, and 0.717 against 0.720), locating the difference in information supplied, not model family. Rankings were consistent across folds, seeds and conditioning schemes (Spearman rho = 0.989-1.000), and removing top-ranked TreeSHAP features harmed AUC more than random removal, though split-gain and permutation rankings performed comparably. Student-level examples are illustrative interpretations, not validated recommendations.
Knowledge tracing in introductory programming is commonly framed as predicting whether a student will eventually solve the next problem. While useful, this approach reduces rich programming activity to correctness labels and offers limited support for instructional interpretation. This study examines whether learner mo...
Kehinde D. Aruleba, S. Oyelere, F. J. Agbo et al.· Proceedings of the 2026 Unit...· 0 citations
Knowledge Tracing (KT) is essential in online education for modeling learners’ evolving knowledge states to support personalized instruction. However, conventional KT approaches often exhibit instability when confronted with abrupt shifts in learner performance—such as sudden errors amid consistent success or unexp...
Bo He, Zhi-Jun Huang, Shengyingjie Liu· Scientific Reports· 0 citations
This paper proposes a straightforward model class, knowledge tracing set transformers (KTSTs), specifically addressing predictive performance in knowledge tracing tasks, and introduces learnable ALiBi and MHSA aggregation, which simplifies and improves upon a prevalent attention mechanism in knowledge tracing.
Kai Neubauer, Yannick Rudolph, Ulf Brefeld· 1 citation
Knowledge tracing models usually use response correctness as a central observation for estimating students'latent knowledge states. However, the same correct or incorrect response may arise from different behavioral contexts, such as rapid guessing, hint use, or repeated attempts. Treating correctness as uniformly info...
Knowledge tracing aims to infer students’ latent knowledge states from historical interaction sequences and serves as a fundamental technique for personalized learning and intelligent assessment. However, existing methods predominantly rely on sequence-level modeling and fail to adequately capture the complex interplay...
Ling-Ling Zi, Jun-Wen Liang, Xin Cong· Journal of King Saud Univers...· 0 citations
AMDKT is proposed, an interpretable dual-stream Transformer model grounded in the Student Proficiency–Item Competency Matching (SPIM) mechanism that achieves AUC performance comparable to the state-of-the-art AKT model, and obtains statistically superior results against DKT, DKVMN, DEEP-IRT, and DIMKT on most datasets.
Shu-Wen Huang, Ruheng Xia, Jin Han· Mathematics· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026