Fine-Tuning Large Language Models for Educational Support: Leveraging Gagne's Nine Events of Instruction for Lesson Planning

2025-03-12

AI Summary

This study addresses the challenge of enhancing lesson preparation quality in compulsory mathematics education by proposing a pedagogy-driven large language model (LLM) augmentation method. Methodologically, it pioneers the structural encoding of Gagné’s Nine Events of Instruction into a Chain-of-Thought (CoT) prompting paradigm and integrates LoRA-based fine-tuning on a custom-built educational instruction dataset—aligned with national curriculum standards and annotated for instructional events. The primary contribution is the development of the first interpretable AI framework for lesson plan generation grounded in classical pedagogical theory. Empirical results demonstrate substantial improvements in LLM accuracy and pedagogical appropriateness across all nine core instructional tasks—including learning objective formulation, content sequencing, and feedback design—enabling scientifically grounded, verifiable, and traceable automated lesson planning.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Effective lesson planning is crucial in education process, serving as the cornerstone for high-quality teaching and the cultivation of a conducive learning atmosphere. This study investigates how large language models (LLMs) can enhance teacher preparation by incorporating them with Gagne's Nine Events of Instruction, especially in the field of mathematics education in compulsory education. It investigates two distinct methodologies: the development of Chain of Thought (CoT) prompts to direct LLMs in generating content that aligns with instructional events, and the application of fine-tuning approaches like Low-Rank Adaptation (LoRA) to enhance model performance. This research starts with creating a comprehensive dataset based on math curriculum standards and Gagne's instructional events. The first method involves crafting CoT-optimized prompts to generate detailed, logically coherent responses from LLMs, improving their ability to create educationally relevant content. The second method uses specialized datasets to fine-tune open-source models, enhancing their educational content generation and analysis capabilities. This study contributes to the evolving dialogue on the integration of AI in education, illustrating innovative strategies for leveraging LLMs to bolster teaching and learning processes.

Problem

• Enhancing teacher preparation using large language models.
• Integrating Gagne's Nine Events of Instruction with LLMs.
• Improving educational content generation in mathematics education.

Innovation

• Fine-tuning LLMs with LoRA for education
• Using CoT prompts to align with Gagne's events
• Creating datasets based on math curriculum standards