The study investigates how a single mastery threshold can produce divergent outcomes across different knowledge tracing (KT) models. By evaluating six KT models on four datasets with thresholds ranging from 0.50 to 0.99, the authors find that Bayesian Knowledge Tracing (BKT) is relatively insensitive to threshold changes, whereas neural models become increasingly selective as thresholds rise. The optimal threshold varies widely across models and instructional settings, and stricter thresholds can disproportionately limit advancement for weaker students.
arXiv:2606. 15349v1 Announce Type: cross Abstract: Standardized examinations are typically treated as uniform syllabus coverage problems.
arXiv:2509. 21514v4 Announce Type: replace Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy.
The study clusters 5,000 EdNet-KT3 learners into eight study‑strategy groups based on early‑session behaviors such as resource use, revision, video watching, and problem practice. These clusters predict later engagement metrics—like continued practice and session completion—but do not reliably forecast later unassisted accuracy or mastery. The findings suggest that behavioral clustering captures learning styles and engagement patterns rather than knowledge gains.
The paper investigates how teacher signals influence parameter updates in Multi‑Teacher On‑Policy Distillation (MOPD) by analyzing Qwen3‑1.7B and SmolLM3‑3B. It shows that loss averaging, Adam’s first‑moment bias, BF16 rounding, and the choice of averaging rule all shape the gradients and ultimately affect task performance. The study quantifies these effects, revealing, for example, that token‑averaging favors longer responses and that BF16 rounding masks most weight changes.
arXiv:2608.21668v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training...
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63. 0-68.
arXiv:2608. 09826v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.
The paper introduces a validation protocol for knowledge‑tracing models that jointly assesses predictive performance, explanation stability, and faithfulness. Using engineered behavioral features from ASSISTments data, the authors compare an XGBoost model explained with TreeSHAP against four deep‑learning baselines, finding comparable predictive accuracy when information is matched and demonstrating that TreeSHAP rankings are stable and impactful. The study highlights how data preprocessing (e.g., rebuilding the 2009 dataset) can affect both model performance and explanation outcomes.
arXiv:2609.37326v1 Announce Type: new Abstract: On-policy distillation, where a student learns from a stronger teacher's feedback on its own outputs, is a common way to pass reasoning to smaller mode...
arXiv:2605. 21629v2 Announce Type: replace-cross Abstract: How much have students' ordinary learning processes shifted in response to generative AI, and how does that affect their durable learning outcomes?
arXiv:2608. 03206v1 Announce Type: cross Abstract: Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS).
arXiv:2604. 04251v2 Announce Type: replace Abstract: Intelligent tutoring systems increasingly rely on reinforcement learning to personalise instruction, yet optimising for observable engagement signals can systematically decouple learner activity from genuine knowledge acquisition.