Empowering ChatGPTwith a guidance-based approachin MTPE learning: effect on student translators’cognitive process, final translation quality, and learning motivation

ChatGPT shows significant potential in machine translation and post-editing (MTPE), prompting discussions on its integration into translator education. However, concerns exist about students’ over-reliance, which can hinder their independent thinking, genuine learning, and overall translation quality. To address this, the study introduces a guidance-based ChatGPT MTPE learning approach inspired by Lee et al. (2024). This model encourages students to articulate their initial thoughts on translation and MTPE tasks before consulting ChatGPT and to use its feedback interactively to refine their strategies. A quasi-experimental study involving 30 first-year translation postgraduates was conducted to examine the effects of the guidance-based approach on student translators’ cognitive processes, final translation quality, and learning motivation, compared to traditional ChatGPT MTPE methods, over a seven-week ChatGPT practicum. Data were collected using eye-tracking, translation quality assessments, and the questionnaire.