Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction

TL;DR

This paper introduces a difficulty-focused contrastive learning approach and an LLM-based framework to improve knowledge tracing models by accurately predicting question and concept difficulty levels, especially for unseen data.

Contribution

It proposes novel contrastive learning and difficulty prediction methods that enhance KT model performance and difficulty estimation accuracy.

Findings

Enhanced KT model performance demonstrated in ablation studies

Effective difficulty prediction for unseen data achieved

Complex language-difficulty relationships identified as an area for future research

Abstract

This paper presents novel techniques for enhancing the performance of knowledge tracing (KT) models by focusing on the crucial factor of question and concept difficulty level. Despite the acknowledged significance of difficulty, previous KT research has yet to exploit its potential for model optimization and has struggled to predict difficulty from unseen data. To address these problems, we propose a difficulty-centered contrastive learning method for KT models and a Large Language Model (LLM)-based framework for difficulty prediction. These innovative methods seek to improve the performance of KT models and provide accurate difficulty estimates for unseen data. Our ablation study demonstrates the efficacy of these techniques by demonstrating enhanced KT model performance. Nonetheless, the complex relationship between language and difficulty merits further investigation.