Connecting Feedback to Choice: Understanding Educator Preferences in GenAI vs. Human-Created Lesson Plans in K-12 Education - A Comparative Analysis

This study conducts a comparative evaluation of K-12 math lesson plans created by human curriculum designers versus those generated by fine-tuned LLaMA-2-13b and customized GPT-4 models, using educator preference ratings across multiple instructional dimensions (warm-up, main task, cool-down, overall quality). Through mixed-methods analysis including quantitative preference data and qualitative thematic coding, the research examines how AI-generated lesson plans compare to human-authored ones across different grade levels.

As generative AI (GenAI) models are increasingly explored for educational applications, understanding educator preferences for AI-generated lesson plans is critical for their effective integration into K-12 instruction. This exploratory study compares lesson plans authored by human curriculum designers, a fine-tuned LLaMA-2-13b model trained on K-12 content, and a customized GPT-4 model to evaluate their pedagogical quality across multiple instructional measures: warm-up activities, main tasks,

Study Type

Source

Framework Categories

Tool Types

Tags