Using Large Language Models to Provide Explanatory Feedback to Human Tutors
Abstract
Research demonstrates learners engaging in the process of producing explanations to support their reasoning can have a positive impact on learning. This work-in-progress demonstrates considerable accuracy in binary classification for corrective feedback of effective, or effort-based praise responses.
Questions this source addresses
- How can large language models be used to classify whether a human tutor's praise response is effective or effort-based, rather than person-based?
- In what ways can automated explanatory feedback help train human tutors to give higher-quality corrective feedback in real time?
- What role does explanatory (versus purely corrective) feedback play in promoting deeper cognitive processing during tutoring interactions?
- Why does having learners generate explanations for their reasoning improve learning outcomes, and how does this generation effect relate to germane cognitive load?