Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Xinyi, Ju, Kexin Phyllis, Dudley, Mitchell, Sano, Larissa, Wang, Xu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.16820
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911464082636800
author Lu, Xinyi
Ju, Kexin Phyllis
Dudley, Mitchell
Sano, Larissa
Wang, Xu
author_facet Lu, Xinyi
Ju, Kexin Phyllis
Dudley, Mitchell
Sano, Larissa
Wang, Xu
contents Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to AI-mediated versus human-provided feedback. We address this gap through a randomized controlled trial in a large introductory economics course (N=354), where we introduce and deploy FeedbackWriter - a system that generates AI suggestions to teaching assistants (TAs) while they provide feedback on students' knowledge-intensive essays. TAs have the full capacity to adopt, edit, or dismiss the suggestions. Students were randomly assigned to receive either handwritten feedback from TAs (baseline) or AI-mediated feedback where TAs received suggestions from FeedbackWriter. Students revise their drafts based on the feedback, which is further graded. In total, 1,366 essays were graded using the system. We found that students receiving AI-mediated feedback produced significantly higher-quality revisions, with gains increasing as TAs adopted more AI suggestions. TAs found the AI suggestions useful for spotting gaps and clarifying rubrics.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16820
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course
Lu, Xinyi
Ju, Kexin Phyllis
Dudley, Mitchell
Sano, Larissa
Wang, Xu
Human-Computer Interaction
Artificial Intelligence
Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to AI-mediated versus human-provided feedback. We address this gap through a randomized controlled trial in a large introductory economics course (N=354), where we introduce and deploy FeedbackWriter - a system that generates AI suggestions to teaching assistants (TAs) while they provide feedback on students' knowledge-intensive essays. TAs have the full capacity to adopt, edit, or dismiss the suggestions. Students were randomly assigned to receive either handwritten feedback from TAs (baseline) or AI-mediated feedback where TAs received suggestions from FeedbackWriter. Students revise their drafts based on the feedback, which is further graded. In total, 1,366 essays were graded using the system. We found that students receiving AI-mediated feedback produced significantly higher-quality revisions, with gains increasing as TAs adopted more AI suggestions. TAs found the AI suggestions useful for spotting gaps and clarifying rubrics.
title AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2602.16820