Skip to main content Skip to navigation

Exploring EFL Secondary Students' AI-generated Text Editing While Composition Writing

Project Overview

This document examines the significant role of generative AI in enhancing the writing processes of English as a Foreign Language (EFL) students, particularly focusing on secondary students in Hong Kong. It reveals that these students do not merely accept AI-generated text but actively interact with it, engaging in complex editing processes during their composition writing. The research categorizes the types of edits made by students and identifies distinct editing patterns, emphasizing the need for educators to modify their writing pedagogies to incorporate explicit teaching methods related to AI text editing strategies. This adaptation is essential to equip students with the skills necessary to navigate and refine AI-generated content effectively, thus maximizing the educational benefits of generative AI in language learning contexts. The findings underscore the potential of generative AI not just as a tool for content generation, but as an integral component in developing critical writing skills among EFL learners.

Key Applications

AI-assisted writing workshop utilizing generative AI tools such as chatbots.

Context: EFL secondary education in Hong Kong, targeting students aged 12-18.

Implementation: Students participated in a two-hour workshop where they learned prompt engineering and utilized AI tools to draft and edit compositions.

Outcomes: Students demonstrated active engagement with AI-generated text, showing complex editing behaviors and cognitive processes.

Challenges: Concerns about academic integrity and maintaining authorial voice while using AI in writing.

Implementation Barriers

Ethical

Concerns regarding academic integrity and the potential for students to submit unedited AI-generated compositions.

Proposed Solutions: Educators should focus on teaching explicit AI-generated text editing strategies and fostering student agency.

Cognitive

EFL students face challenges in maintaining their authorial voice and managing unsolicited AI interventions.

Proposed Solutions: Instructors can model prompt engineering and encourage strategic engagement with AI-generated text.

Project Team

David James Woo

Researcher

Yangyang Yu

Researcher

Kai Guo

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: David James Woo, Yangyang Yu, Kai Guo

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies