Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs
This work addresses the problem of efficient and accurate prediction of student responses for educational learning platforms, providing an incremental improvement over existing large language models.
The authors tackled the problem of predicting student responses to questions, and found that specialized knowledge tracing models outperform large language models, achieving higher accuracy and F1 scores while being orders of magnitude faster and cheaper to deploy. The knowledge tracing models achieved superior results, with specific numbers on accuracy and cost not provided.
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.