Classroom AI: Large Language Models as Grade-Specific Teachers

TL;DR

This paper presents a framework for fine-tuning large language models to generate age-appropriate educational content across various grade levels, enhancing personalized learning and addressing global teacher shortages.

Contribution

It introduces a novel method combining readability metrics and clustering to adapt LLM explanations to specific educational levels, improving grade-level alignment.

Findings

35.64 percentage point increase in grade-level accuracy

Maintains factual correctness in age-appropriate responses

Substantial improvement over prompt-based methods

Abstract

Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds of millions of children, but they fail to provide grade-appropriate responses for students at different educational levels. We introduce a framework for finetuning LLMs to generate age-appropriate educational content across six grade levels, from lower elementary to adult education. Our framework successfully adapts explanations to match students' comprehension capacities without sacrificing factual correctness. This approach integrates seven established readability metrics through a clustering method and builds a comprehensive dataset for grade-specific content generation. Evaluations across multiple datasets with 208 human participants demonstrate substantial improvements in grade-level alignment, achieving a 35.64 percentage point increase compared to prompt-based methods while maintaining response accuracy. AI-assisted learning tailored to different grade levels has the potential to advance educational engagement and equity.