DKT2: Revisiting Applicable and Comprehensive Knowledge Tracing in Large-Scale Data

TL;DR

DKT2 introduces a novel knowledge tracing model leveraging xLSTM, Rasch model, and IRT to improve interpretability and performance in large-scale educational data, addressing limitations of previous DLKT models.

Contribution

The paper presents DKT2, a new KT model that enhances applicability and interpretability using xLSTM, Rasch model, and IRT, outperforming existing models on large datasets.

Findings

DKT2 outperforms 18 baseline models in prediction tasks.

Incorporates IRT for better interpretability of knowledge states.

Demonstrates effectiveness across three large-scale datasets.

Abstract

Knowledge Tracing (KT) is a fundamental component of Intelligent Tutoring Systems (ITS), enabling the modeling of students' knowledge states to predict future performance. The introduction of Deep Knowledge Tracing (DKT), the first deep learning-based KT (DLKT) model, has brought significant advantages in terms of applicability and comprehensiveness. However, recent DLKT models, such as Attentive Knowledge Tracing (AKT), have often prioritized predictive performance at the expense of these benefits. While deep sequential models like DKT have shown potential, they face challenges related to parallel computing, storage decision modification, and limited storage capacity. To address these limitations, we propose DKT2, a novel KT model that leverages the recently developed xLSTM architecture. DKT2 enhances applicable input representation using the Rasch model and incorporates Item Response Theory (IRT) for output interpretability, allowing for the decomposition of learned knowledge into familiar and unfamiliar knowledge. By integrating this knowledge with predicted questions, DKT2 generates comprehensive knowledge states. Extensive experiments conducted across three large-scale datasets demonstrate that DKT2 consistently outperforms 18 baseline models in various prediction tasks, underscoring its potential for real-world educational applications. This work bridges the gap between theoretical advancements and practical implementation in KT. Our code and datasets are fully available at https://github.com/zyy-2001/DKT2.