COGENT: A Curriculum-oriented Framework for Generating Grade-appropriate Educational Content

TL;DR

COGENT is a framework that generates grade-appropriate educational content by aligning with curriculum standards, controlling readability, and increasing engagement, with evaluations showing it produces high-quality, suitable passages.

Contribution

This work introduces COGENT, a novel curriculum-oriented framework for generating educational content that is grade-appropriate, engaging, and aligned with curriculum standards.

Findings

COGENT produces passages that match or surpass human references in quality.

The framework effectively controls readability and curriculum alignment.

Experimental evaluations confirm the quality and appropriateness of generated content.

Abstract

While Generative AI has demonstrated strong potential and versatility in content generation, its application to educational contexts presents several challenges. Models often fail to align with curriculum standards and maintain grade-appropriate reading levels consistently. Furthermore, STEM education poses additional challenges in balancing scientific explanations with everyday language when introducing complex and abstract ideas and phenomena to younger students. In this work, we propose COGENT, a curriculum-oriented framework for generating grade-appropriate educational content. We incorporate three curriculum components (science concepts, core ideas, and learning objectives), control readability through length, vocabulary, and sentence complexity, and adopt a ``wonder-based'' approach to increase student engagement and interest. We conduct a multi-dimensional evaluation via both LLM-as-a-judge and human expert analysis. Experimental results show that COGENT consistently produces grade-appropriate passages that are comparable or superior to human references. Our work establishes a viable approach for scaling adaptive and high-quality learning resources.