AIEDHK
← Назад к новостям исследований

#feedback

feedback

2 статей

A trainee and supervisor review a simulated text conversation and annotated listening-skills notes in a bright professional-training room.
Конференционная статья2026
Конференционная статья 136

Simulated counseling practice benefited from structured AI feedback, with the clearest group difference in empathy

Ryan Louie, Raj Sanjay Shah, Ifdita Hasan Orney, Juan Pablo Pacheco, Emma Brunskill, Diyi Yang

CHI 2026

A randomized study of 94 novices compared practice with an AI-simulated counseling client with the same practice plus AI feedback. The clearest between-group result favored feedback on an automated empathy measure; other skills showed more limited or within-group changes. The experiment tested immediate behavior in simulated text conversations, with classifier-based assessment and no conventional-training comparator. It therefore informs training design rather than establishing readiness to counsel real clients.

simulation-based learningfeedbackprofessional education
Читать резюме на 500 слов →
A writing tutor discusses two annotated drafts with a graduate student beside a laptop, with a sunlit Hong Kong waterfront visible through the window.
Журнальная статья2025
Журнальная статья 120

AI writing feedback improved revised drafts, while adding teacher feedback did not yield a clear overall advantage

Linqian Ding, Di Zou, Lucas Kohnke

Education and Information Technologies

A study of 77 graduate students in Hong Kong compared ChatGPT feedback with teacher-refined ChatGPT feedback on a literature-review assignment. Both groups improved their revised drafts. The combined approach produced a significant grammar advantage, but no significant overall improvement advantage between groups. Because the study assessed one assignment without an unaided transfer test, the findings concern revision quality rather than established long-term writing development.

academic writingfeedbackHong Kong
Читать резюме на 500 слов →