Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations

TL;DR

This paper introduces Assertion Enhanced Few-Shot Learning, a novel prompting method for large language models that improves the quality and accuracy of educational explanations in intelligent tutoring systems.

Contribution

It proposes a new assertion-based prompting technique that enhances few-shot learning for generating educational explanations, supported by empirical evaluation with teachers.

Findings

15% improvement in explanation accuracy

Higher-quality explanations as rated by teachers

Ablation study on assertion impact

Abstract

Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to imbue Intelligent Tutoring Systems with this ability using few-shot learning capability of Large Language Models. Our work proposes a novel prompting technique, Assertion Enhanced Few-Shot Learning, to facilitate the generation of accurate, detailed oriented educational explanations. Our central hypothesis is that, in educational domain, few-shot demonstrations are necessary but not a sufficient condition for quality explanation generation. We conducted a study involving 12 in-service teachers, comparing our approach to Traditional Few-Shot Learning. The results show that Assertion Enhanced Few-Shot Learning improves explanation accuracy by 15% and yields higher-quality explanations, as evaluated by teachers. We also conduct a qualitative ablation study to factor the impact of assertions to provide educator-friendly prompting guidelines for generating explanations in their domain of interest.