CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models

TL;DR

This paper introduces CIKT, a novel framework that leverages large language models for collaborative, iterative, and explainable knowledge tracing, significantly improving prediction accuracy and scalability in educational settings.

Contribution

The paper proposes a dual-component, iterative framework using LLMs for enhanced prediction and explainability in knowledge tracing, addressing limitations of traditional methods.

Findings

Improved prediction accuracy on multiple datasets.

Enhanced explainability through dynamic user profiles.

Better scalability compared to existing models.

Abstract

Knowledge Tracing (KT) aims to model a student's learning state over time and predict their future performance. However, traditional KT methods often face challenges in explainability, scalability, and effective modeling of complex knowledge dependencies. While Large Language Models (LLMs) present new avenues for KT, their direct application often struggles with generating structured, explainable student representations and lacks mechanisms for continuous, task-specific refinement. To address these gaps, we propose Collaborative Iterative Knowledge Tracing (CIKT), a framework that harnesses LLMs to enhance both prediction accuracy and explainability. CIKT employs a dual-component architecture: an Analyst generates dynamic, explainable user profiles from student historical responses, and a Predictor utilizes these profiles to forecast future performance. The core of CIKT is a synergistic optimization loop. In this loop, the Analyst is iteratively refined based on the predictive accuracy of the Predictor, which conditions on the generated profiles, and the Predictor is subsequently retrained using these enhanced profiles. Evaluated on multiple educational datasets, CIKT demonstrates significant improvements in prediction accuracy, offers enhanced explainability through its dynamically updated user profiles, and exhibits improved scalability. Our work presents a robust and explainable solution for advancing knowledge tracing systems, effectively bridging the gap between predictive performance and model transparency.