Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs

TL;DR

Specialized knowledge tracing models outperform large language models in predicting student responses, offering higher accuracy, faster inference, and lower deployment costs, emphasizing the importance of domain-specific models in education.

Contribution

This study systematically compares LLMs and KT models, demonstrating KT models' superior performance and efficiency in domain-specific educational response prediction tasks.

Findings

KT models outperform LLMs in accuracy and F1 scores

LLMs are significantly slower and more costly to deploy

Domain-specific KT models are more suitable for educational prediction tasks

Abstract

Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions. One of the key approaches to do this has been through the use of knowledge tracing (KT) models. These are small, domain-specific, temporal models trained on student question-response data. KT models are optimised for high accuracy on specific educational domains and have fast inference and scalable deployments. The rise of Large Language Models (LLMs) motivates us to ask the following questions: (1) How well can LLMs perform at predicting students' future responses to questions? (2) Are LLMs scalable for this domain? (3) How do LLMs compare to KT models on this domain-specific task? In this paper, we compare multiple LLMs and KT models across predictive performance, deployment cost, and inference speed to answer the above questions. We show that KT models outperform LLMs with respect to accuracy and F1 scores on this domain-specific task. Further, we demonstrate that LLMs are orders of magnitude slower than KT models and cost orders of magnitude more to deploy. This highlights the importance of domain-specific models for education prediction tasks and the fact that current closed source LLMs should not be used as a universal solution for all tasks.