Development of a Dual-Layer Feedback System for EFL Writing: From the Perspective of Self-Regulated Learning

Abstract

This study aims to develop a writing support system that utilizes large-scale language modeling (LLM) techniques to enhance self-regulated learning (SRL) for English as a foreign language (EFL) learners. We designed and implemented a support system utilizing GPT-4 to generate structured, dual-layer feedback that addresses language aspects and stages of forethought, performance, and self-reflection for SRL models. This integrated approach addresses gaps identified in traditional feedback methods by supporting immediate language improvement while promoting the development of self-regulation skills necessary for long-term writing proficiency.