Explainable Few-shot Knowledge Tracing

TL;DR

This paper introduces a new approach to knowledge tracing that uses large language models to perform explainable, few-shot student performance prediction, addressing real-world scenarios with limited data.

Contribution

It proposes a cognition-guided framework leveraging LLMs for explainable, few-shot knowledge tracing, filling a gap in current deep learning-based methods.

Findings

LLMs perform comparably or better than traditional methods on key datasets.

The framework provides natural language explanations of student knowledge states.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Knowledge tracing (KT), aiming to mine students' mastery of knowledge by their exercise records and predict their performance on future test questions, is a critical task in educational assessment. While researchers achieved tremendous success with the rapid development of deep learning techniques, current knowledge tracing tasks fall into the cracks from real-world teaching scenarios. Relying heavily on extensive student data and solely predicting numerical performances differs from the settings where teachers assess students' knowledge state from limited practices and provide explanatory feedback. To fill this gap, we explore a new task formulation: Explainable Few-shot Knowledge Tracing. By leveraging the powerful reasoning and generation abilities of large language models (LLMs), we then propose a cognition-guided framework that can track the student knowledge from a few student records while providing natural language explanations. Experimental results from three widely used datasets show that LLMs can perform comparable or superior to competitive deep knowledge tracing methods. We also discuss potential directions and call for future improvements in relevant topics.