MetaTOC stay on top of your field, easily

When ChatGPT gets it wrong: investigating third position repair by L2 learners at varying proficiency levels

,

Language Teaching Research

Published online on

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 ...