Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/13144
Title: Comparing layered and non-layered LLM-generated feedback: Effects on learning gains and learner perceptions
Other Titles: Comparing Layered and Non-Layered LLM-Generated Feedback: Effects on Learning Gains and Learner Perceptions
Authors: Cao, Jie
Zhao, Chloe Qianhui
Lin, Jionghao
Koedinger, Kenneth R.
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 3052-3054
Publisher: International Society of the Learning Sciences
Citation: Cao, J., Zhao, C. Q., Lin, J., & Koedinger, K. R. (2026). Comparing layered and non-layered LLM-generated feedback: Effects on learning gains and learner perceptions. In Litts, B. K., DeLiema, D., Lee, C., Krist, S. Mawasi, A., Martin, L., & Kumpulainen, K. (Eds.), Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026 (pp. 3052-3054). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: This study investigated how layered versus non-layered large language model–generated feedback influences learning gains across task types and learner perceptions through an experimental design. Results indicated that non-layered feedback produced greater learning gains on multiple-choice questions, while no significant difference for open-ended tasks. However, learners receiving layered feedback reported a stronger sense of connection with the feedback provider, although perceived acceptance did not differ.
Description: POSTER
URI: https://doi.org/10.22318/icls2026.727389
https://repository.isls.org/handle/1/13144
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_3052-3054.pdf270.71 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.