#860: Comparing Layered and Non-Layered LLM-Generated Feedback: Effects on Learning Gains and Learner Perceptions

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.