HISE-KT: Synergizing Heterogeneous Information Networks and LLMs for Explainable Knowledge Tracing with Meta-Path Optimization

TL;DR

HISE-KT innovatively combines heterogeneous information networks and large language models to enhance knowledge tracing accuracy and provide explainable, evidence-based student performance predictions.

Contribution

The paper introduces a novel framework that integrates HINs with LLMs, including automated meta-path quality assessment and a student retrieval mechanism for improved prediction and interpretability.

Findings

HISE-KT outperforms existing methods in prediction accuracy.

The framework provides evidence-backed explanations.

Automated meta-path filtering improves data quality.

Abstract

Knowledge Tracing (KT) aims to mine students' evolving knowledge states and predict their future question-answering performance. Existing methods based on heterogeneous information networks (HINs) are prone to introducing noises due to manual or random selection of meta-paths and lack necessary quality assessment of meta-path instances. Conversely, recent large language models (LLMs)-based methods ignore the rich information across students, and both paradigms struggle to deliver consistently accurate and evidence-based explanations. To address these issues, we propose an innovative framework, HIN-LLM Synergistic Enhanced Knowledge Tracing (HISE-KT), which seamlessly integrates HINs with LLMs. HISE-KT first builds a multi-relationship HIN containing diverse node types to capture the structural relations through multiple meta-paths. The LLM is then employed to intelligently score and filter meta-path instances and retain high-quality paths, pioneering automated meta-path quality assessment. Inspired by educational psychology principles, a similar student retrieval mechanism based on meta-paths is designed to provide a more valuable context for prediction. Finally, HISE-KT uses a structured prompt to integrate the target student's history with the retrieved similar trajectories, enabling the LLM to generate not only accurate predictions but also evidence-backed, explainable analysis reports. Experiments on four public datasets show that HISE-KT outperforms existing KT baselines in both prediction performance and interpretability.