Which Feedback Works for Whom? Differential Effects of LLM-Generated Feedback Elements Across Learner Profiles
This research addresses the need for personalized feedback design in education by showing how to adapt LLM-generated feedback to different learner personalities, though it is incremental as it builds on existing work in educational feedback and LLMs.
The study investigated how specific elements of LLM-generated feedback, such as tone and information coverage, affect learning outcomes and acceptance among high school students, finding that effective feedback elements share common patterns for learning but subjective preferences vary based on personality traits.
Large language models (LLMs) show promise for automatically generating feedback in education settings. However, it remains unclear how specific feedback elements, such as tone and information coverage, contribute to learning outcomes and learner acceptance, particularly across learners with different personality traits. In this study, we define six feedback elements and generate feedback for multiple-choice biology questions using GPT-5. We conduct a learning experiment with 321 first-year high school students and evaluate feedback effectiveness using two learning outcomes measures and subjective evaluations across six criteria. We further analyze differences in how feedback acceptance varies across learners based on Big Five personality traits. Our results show that effective feedback elements share common patterns supporting learning outcomes, while learners' subjective preferences differ across personality-based clusters. These findings highlight the importance of selecting and adapting feedback elements according to learners' personality traits when we design LLM-generated feedback, and provide practical implications for personalized feedback design in education.