International Group for the Psychology of Mathematics Education (PME)

Proceedings of the International Group for the Psychology of Mathematics Education · Volume 1

Chatgpt’s Pedagogical Approach in Mathematics

Laurie H Rubel, Shimrit Goidel

University of Haifa

49th Annual Conference of the International Group for the Psychology of Mathematics Education, PME 2026Helsinki27 July 2026 - 1 August 2026pp. 1251–1258ISSN 2790-36482026Scopus conference code 336559
⬇ Download PDF

Abstract

We investigate ChatGPT-4's pedagogical approach by studying mathematics lessons it generates, with respect to school context descriptors. We generated 45 eighth-grade probability lesson plans across three conditions: a baseline prompt, a "Successful School" context, and a "Struggling School" context. Content analysis of the lesson plans and 368 teacher-action verbs suggest that the LLM tends towards direct instruction and shifts its responses to school descriptors. "Successful School" prompts generated lessons with additional mathematics concepts and advanced technology integration, whereas "Struggling School" prompts produced lessons with more monitoring of students’ progress, reinforcement activities, and attention to socioemotional support.

Keywords

artificial intelligencelarge language modelspedagogical approachequity in mathematics

Recommended citation

Rubel, L., & Goidel, S. (2026). Chatgpt’s Pedagogical Approach in Mathematics. In Krzywacki H., Hähkiöniemi M., Haataja E., Hannula M.S., Hästö P. (Eds.), Proceedings of the International Group for the Psychology of Mathematics Education, Volume 1 (pp. 1251–1258). Psychology of Mathematics Education (PME). ISSN 2790-3648.
BibTeXRIS

← All PME 49 Research Reports