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

Xingcheng Fu, Shengpeng Wang, Yisen Gao, Xianxian LI, Chunpei Li, Qingyun Sun, Dongran Yu

Abstract:

Knowledge Tracing (KT) diagnoses students’ concept mas
tery through continuous learning state monitoring in educa
tion. Existing methods primarily focus on studying behav
ioral sequences based on ID or textual information. While
existing methods rely on ID-based sequences or shallow tex
tual features, they often fail to capture (1) the hierarchical
evolution of cognitive states and (2) individualized prob
lem 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 ex
plicitly constructs hierarchical dependencies of knowledge
points; the student agent simulates learning behaviors to gen
erate 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 dif
f
iculty and forgetting patterns. Finally, by optimizing hyper
bolic curvature, we explicitly model the tree-like hierarchical
structure of knowledge points, precisely characterizing dif
ferences 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.