GPT-4 as a Homework Tutor can Improve Student Engagement and Learning Outcomes
Alessandro Vanzo, Sankalan Pal Chowdhury, Mrinmaya Sachan

TL;DR
This study demonstrates that GPT-4 can effectively serve as an interactive homework tutor for high-school students learning English, leading to improved engagement and learning outcomes in real-world educational settings.
Contribution
The paper introduces a scalable prompting strategy for GPT-4 to conduct interactive homework sessions with minimal content preparation, tested through a randomized controlled trial.
Findings
Significant improvement in grammar learning outcomes
Increased student engagement and satisfaction
High willingness to continue using GPT-4 tutoring
Abstract
This work contributes to the scarce empirical literature on LLM-based interactive homework in real-world educational settings and offers a practical, scalable solution for improving homework in schools. Homework is an important part of education in schools across the world, but in order to maximize benefit, it needs to be accompanied with feedback and followup questions. We developed a prompting strategy that enables GPT-4 to conduct interactive homework sessions for high-school students learning English as a second language. Our strategy requires minimal efforts in content preparation, one of the key challenges of alternatives like home tutors or ITSs. We carried out a Randomized Controlled Trial (RCT) in four high-school classes, replacing traditional homework with GPT-4 homework sessions for the treatment group. We observed significant improvements in learning outcomes, specifically…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsDiverse Education Studies and Reforms
