A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education

This systematic review analyzes 30 empirical studies published between 2021-2024 that explore the use of LLMs with prompt engineering techniques in K-12 STEM education, examining prompting strategies, model types, evaluation methods, and limitations. The review identifies how different prompting approaches (zero-shot, few-shot, chain-of-thought) are applied to educational tasks and their effectiveness in teaching and learning contexts.

Large language models (LLMs) have the potential to enhance K-12 STEM education by improving both teaching and learning processes. While previous studies have shown promising results, there is still a lack of comprehensive understanding regarding how LLMs are effectively applied, specifically through prompt engineering-the process of designing prompts to generate desired outputs. To address this gap, our study investigates empirical research published between 2021 and 2024 that explores the use o

Study Type

Source

Framework Categories

Tool Types

Tags