Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space

TL;DR

This paper introduces L-HAKT, a novel knowledge tracing framework leveraging large language models and hyperbolic space to better capture hierarchical cognitive states and individual problem perceptions, improving educational predictions.

Contribution

It proposes a hierarchical, hyperbolic space modeling approach using LLMs for knowledge tracing, explicitly capturing cognitive hierarchies and individual differences, which previous methods lacked.

Findings

L-HAKT outperforms existing methods on four real-world datasets.

Contrastive learning in hyperbolic space improves feature alignment.

Explicit hierarchical modeling enhances understanding of learning processes.

Abstract

Knowledge Tracing (KT) diagnoses students' concept mastery through continuous learning state monitoring in education.Existing methods primarily focus on studying behavioral sequences based on ID or textual information.While existing methods rely on ID-based sequences or shallow textual features, they often fail to capture (1) the hierarchical evolution of cognitive states and (2) individualized problem difficulty perception due to limited semantic modeling. Therefore, this paper proposes a Large Language Model Hyperbolic Aligned Knowledge Tracing(L-HAKT). First, the teacher agent deeply parses question semantics and explicitly constructs hierarchical dependencies of knowledge points; the student agent simulates learning behaviors to generate synthetic data. Then, contrastive learning is performed between synthetic and real data in hyperbolic space to reduce distribution differences in key features such as question difficulty and forgetting patterns. Finally, by optimizing hyperbolic curvature, we explicitly model the tree-like hierarchical structure of knowledge points, precisely characterizing differences in learning curve morphology for knowledge points at different levels. Extensive experiments on four real-world educational datasets validate the effectiveness of our Large Language Model Hyperbolic Aligned Knowledge Tracing (L-HAKT) framework.