LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models

TL;DR

This paper introduces LessonPlanner, an interactive system that helps novice teachers create pedagogy-driven lesson plans by leveraging large language models and Gagne's Nine Events. Through a formative study and a within-subjects evaluation with 12 participants plus expert interviews with 6 teachers, the authors demonstrate that LessonPlanner improves the quality of lesson plans and reduces planning workload compared to a baseline ChatGPT interface. The work provides empirical evidence on the usefulness of structured outlines, event-based prompts, and a sidebar LLM assistant, while highlighting trust, reliability, and usability considerations. Practical implications include design guidelines for integrating reliable knowledge sources, flexible prompting, and multimodal content to support teacher planning in diverse subjects and educational levels.

Abstract

Preparing a lesson plan, e.g., a detailed road map with strategies and materials for instructing a 90-minute class, is beneficial yet challenging for novice teachers. Large language models (LLMs) can ease this process by generating adaptive content for lesson plans, which would otherwise require teachers to create from scratch or search existing resources. In this work, we first conduct a formative study with six novice teachers to understand their needs for support of preparing lesson plans with LLMs. Then, we develop LessonPlanner that assists users to interactively construct lesson plans with adaptive LLM-generated content based on Gagne's nine events. Our within-subjects study (N=12) shows that compared to the baseline ChatGPT interface, LessonPlanner can significantly improve the quality of outcome lesson plans and ease users' workload in the preparation process. Our expert interviews (N=6) further demonstrate LessonPlanner's usefulness in suggesting effective teaching strategies and meaningful educational resources. We discuss concerns on and design considerations for supporting teaching activities with LLMs.

Figures (13)

• Figure 1: An example lesson plan preparation process. We build an interactive system LessonPlanner to assist teachers with generated content to prepare a documented lesson plan, which can be optionally transformed into slides by users and delivered in their courses.
• Figure 2: Goal-setting page of LessonPlanner, with the illustration of the process of refining lesson goals with LLMs. The text in parentheses serves as a correction to the mistranslated output.
• Figure 3: The lesson-planning interface for LessonPlanner. The text in parentheses serves as a correction to the mistranslated output.
• Figure 4: The subsequent changes or pop-up windows triggered by clicking a button on \ref{['fig:edit']}.
• Figure 5: The process of setting instructional events by users in the lesson-planning interface.