When ChatGPT gets it wrong: investigating third position repair by L2 learners at varying proficiency levels
Published online on April 01, 2026
Abstract
Language Teaching Research, Ahead of Print.
This study explores how 30 Korean English as a foreign language (EFL) learners at three proficiency levels (CEFR A2, B1, and B2) manage third position repair during voice-based role-play tasks with ChatGPT-4. Over 12 hours and 30 minutes of recorded ...
This study explores how 30 Korean English as a foreign language (EFL) learners at three proficiency levels (CEFR A2, B1, and B2) manage third position repair during voice-based role-play tasks with ChatGPT-4. Over 12 hours and 30 minutes of recorded ...