Tag: knowledge tracing

A new graph-based framework groups similar learners and augments sparse data to improve cognitive diagnosis predictions across three public datasets.

A study of 1,000 university learners identified four distinct online English learning behavior patterns and showed that feeding them into ...

A quasi-experimental study of 357 online programming learners found that teacher-governed LLM scaffolding was associated with stronger formative practice and ...

A study of 8,000 students found that a hybrid knowledge-tracing model combining language semantics, dialogue behavior and multidimensional memory achieved ...

A new causal hypergraph state space model builds a digital twin of each learner that removes confounding bias during representation ...

Researchers have developed and validated an AI-driven adaptive learning system that predicts student engagement, forecasts academic achievement, and generates explainable ...

A new study in Frontiers of Digital Education maps how large language models can power truly personalized learning while exposing ...

Researchers in China have shown that large language models can diagnose student knowledge in entirely new subjects without any prior ...

Researchers have reformulated knowledge tracing so large language models can assess a student's understanding from only a few answers while ...

Researchers in China have built an LLM-powered digital human that gives students real-time, personalized tutoring while they watch pre-recorded lectures.