When Scaffolding Breaks: Investigating Student Interaction with LLM-Based Writing Support in Real-Time K-12 EFL Classrooms

TL;DR

This study explores the use of large language models as real-time writing support in K-12 classrooms, revealing benefits in grammar but challenges in engagement, equity, and classroom management.

Contribution

It provides empirical insights into LLM deployment in real classroom settings, highlighting practical challenges and offering design guidelines for inclusive use.

Findings

LLMs improved grammatical correctness in student writing.

Lower-proficiency students felt demotivated and relied more on the system.

Classroom dynamics were affected, with extroverted students dominating attention.

Abstract

Large language models (LLMs) are promising tools for scaffolding students' English writing skills, but their effectiveness in real-time K-12 classrooms remains underexplored. Addressing this gap, our study examines the benefits and limitations of using LLMs as real-time learning support, considering how classroom constraints, such as diverse proficiency levels and limited time, affect their effectiveness. We conducted a deployment study with 157 eighth-grade students in a South Korean middle school English class over six weeks. Our findings reveal that while scaffolding improved students' ability to compose grammatically correct sentences, this step-by-step approach demotivated lower-proficiency students and increased their system reliance. We also observed challenges to classroom dynamics, where extroverted students often dominated the teacher's attention, and the system's assistance made it difficult for teachers to identify struggling students. Based on these findings, we discuss design guidelines for integrating LLMs into real-time writing classes as inclusive educational tools.