Saved in:
Bibliographic Details
Main Authors: Weijers, Ruben, Wu, Denton, Betts, Hannah, Jacod, Tamara, Guan, Yuxiang, Sujaya, Vidya, Dev, Kushal, Goel, Toshali, Delooze, William, Rabbany, Reihaneh, Wu, Ying, Godbout, Jean-François, Pelrine, Kellin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00408
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912302334214144
author Weijers, Ruben
Wu, Denton
Betts, Hannah
Jacod, Tamara
Guan, Yuxiang
Sujaya, Vidya
Dev, Kushal
Goel, Toshali
Delooze, William
Rabbany, Reihaneh
Wu, Ying
Godbout, Jean-François
Pelrine, Kellin
author_facet Weijers, Ruben
Wu, Denton
Betts, Hannah
Jacod, Tamara
Guan, Yuxiang
Sujaya, Vidya
Dev, Kushal
Goel, Toshali
Delooze, William
Rabbany, Reihaneh
Wu, Ying
Godbout, Jean-François
Pelrine, Kellin
contents Generative AI has the potential to transform personalization and accessibility of education. However, it raises serious concerns about accuracy and helping students become independent critical thinkers. In this study, we designed a helpful AI "Peer" to help students correct fundamental physics misconceptions related to Newtonian mechanic concepts. In contrast to approaches that seek near-perfect accuracy to create an authoritative AI tutor or teacher, we directly inform students that this AI can answer up to 40% of questions incorrectly. In a randomized controlled trial with 165 students, those who engaged in targeted dialogue with the AI Peer achieved post-test scores that were, on average, 10.5 percentage points higher - with over 20 percentage points higher normalized gain - than a control group that discussed physics history. Qualitative feedback indicated that 91% of the treatment group's AI interactions were rated as helpful. Furthermore, by comparing student performance on pre- and post-test questions about the same concept, along with experts' annotations of the AI interactions, we find initial evidence suggesting the improvement in performance does not depend on the correctness of the AI. With further research, the AI Peer paradigm described here could open new possibilities for how we learn, adapt to, and grow with AI.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions
Weijers, Ruben
Wu, Denton
Betts, Hannah
Jacod, Tamara
Guan, Yuxiang
Sujaya, Vidya
Dev, Kushal
Goel, Toshali
Delooze, William
Rabbany, Reihaneh
Wu, Ying
Godbout, Jean-François
Pelrine, Kellin
Computers and Society
Artificial Intelligence
Human-Computer Interaction
Generative AI has the potential to transform personalization and accessibility of education. However, it raises serious concerns about accuracy and helping students become independent critical thinkers. In this study, we designed a helpful AI "Peer" to help students correct fundamental physics misconceptions related to Newtonian mechanic concepts. In contrast to approaches that seek near-perfect accuracy to create an authoritative AI tutor or teacher, we directly inform students that this AI can answer up to 40% of questions incorrectly. In a randomized controlled trial with 165 students, those who engaged in targeted dialogue with the AI Peer achieved post-test scores that were, on average, 10.5 percentage points higher - with over 20 percentage points higher normalized gain - than a control group that discussed physics history. Qualitative feedback indicated that 91% of the treatment group's AI interactions were rated as helpful. Furthermore, by comparing student performance on pre- and post-test questions about the same concept, along with experts' annotations of the AI interactions, we find initial evidence suggesting the improvement in performance does not depend on the correctness of the AI. With further research, the AI Peer paradigm described here could open new possibilities for how we learn, adapt to, and grow with AI.
title From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions
topic Computers and Society
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2504.00408