Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning

TL;DR

This paper introduces PLKT, an interpretable knowledge tracing framework using probabilistic embeddings and logical reasoning to improve transparency and performance in predicting student learning outcomes.

Contribution

It proposes a novel probabilistic logical approach to knowledge tracing that enhances interpretability without sacrificing accuracy.

Findings

PLKT outperforms existing KT models in predictive accuracy.

PLKT provides transparent reasoning paths for interpretability.

Probabilistic embeddings model uncertainty effectively.

Abstract

Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy, most models rely on deterministic vector embeddings and opaque latent state transitions, limiting interpretability regarding how specific past behaviors influence predictions. To address this limitation, we propose Probabilistic Logical Knowledge Tracing (PLKT), an interpretable KT framework that formulates prediction as a goal-conditioned evidence reasoning process over historical learning behaviors. Instead of representing knowledge states as deterministic vector embeddings, PLKT employs robust Beta-distributed probabilistic embeddings to represent student knowledge states. This probabilistic foundation allows us to model the uncertainty of historical behaviors and perform explicit logical operations (e.g., conjunction), constructing transparent reasoning paths that reveal how specific past interactions contribute to the prediction. Extensive experiments show that PLKT outperforms state-of-the-art KT methods while achieving superior interpretability. Our code is available at https://anonymous.4open.science/r/PLKT-D3CE/.