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

2025-12-05

AI Summary

This study investigates the efficacy and pedagogical appropriateness of large language models (LLMs) as real-time writing support tools in K–12 English-as-a-foreign-language (EFL) classrooms. Method: A classroom-deployed empirical study was conducted under authentic instructional constraints—including heterogeneous learner proficiency levels and limited class time—to examine LLM-supported writing’s impact on writing performance, motivation, and teacher–student interaction across proficiency levels. Results: While the system significantly improved sentence-level grammatical accuracy, it exacerbated tool dependency among lower-proficiency learners and impaired teachers’ ability to diagnose students’ writing difficulties. Notably, scaffolded LLM feedback triggered adverse motivational effects. Based on these findings, the study proposes design principles for inclusive LLM-based writing support systems—emphasizing differentiated feedback mechanisms, metacognitive prompting, and teacher co-intervention—to advance responsible, educationally grounded LLM integration.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Examining LLM-based writing support effectiveness in K-12 EFL classrooms
• Investigating how classroom constraints impact real-time LLM scaffolding outcomes
• Addressing student demotivation and system reliance issues in LLM-assisted writing

Innovation

• Real-time LLM scaffolding for K-12 EFL writing
• Deployment study in classroom with diverse proficiency levels
• Design guidelines for inclusive LLM integration in education