Neural-Symbolic Knowledge Tracing: Injecting Educational Knowledge into Deep Learning for Responsible Learner Modelling

TL;DR

This paper introduces Responsible-DKT, a neural-symbolic model for learner knowledge tracing that combines symbolic educational rules with deep learning, improving accuracy, interpretability, and pedagogical alignment in educational AI.

Contribution

It presents a novel neural-symbolic approach that integrates symbolic educational knowledge into deep knowledge tracing models, enhancing performance and interpretability.

Findings

Responsible-DKT outperforms baseline models in AUC, especially with limited data.

The model achieves up to 0.90 AUC, improving by 13% over data-driven models.

It provides intrinsic interpretability and aligns predictions with pedagogical principles.

Abstract

The growing use of artificial intelligence (AI) in education, particularly large language models (LLMs), has increased interest in intelligent tutoring systems. However, LLMs often show limited adaptivity and struggle to model learners' evolving knowledge over time, highlighting the need for dedicated learner modelling approaches. Although deep knowledge tracing methods achieve strong predictive performance, their opacity and susceptibility to bias can limit alignment with pedagogical principles. To address this, we propose Responsible-DKT, a neural-symbolic deep knowledge tracing approach that integrates symbolic educational knowledge (e.g., mastery and non-mastery rules) into sequential neural models for responsible learner modelling. Experiments on a real-world dataset of students' math interactions show that Responsible-DKT outperforms both a neural-symbolic baseline and a fully data-driven PyTorch DKT model across training settings. The model achieves over 0.80 AUC with only 10% of training data and up to 0.90 AUC, improving performance by up to 13%. It also demonstrates improved temporal reliability, producing lower early- and mid-sequence prediction errors and the lowest prediction inconsistency rates across sequence lengths, indicating that prediction updates remain directionally aligned with observed student responses over time. Furthermore, the neural-symbolic approach offers intrinsic interpretability via a grounded computation graph that exposes the logic behind each prediction, enabling both local and global explanations. It also allows empirical evaluation of pedagogical assumptions, revealing that repeated incorrect responses (non-mastery) strongly influence prediction updates. These results indicate that neural-symbolic approaches enhance both performance and interpretability, mitigate data limitations, and support more responsible, human-centered AI in education.