Prompting, evaluating, and adapting AI-generated mathematical tasks: Secondary preservice teachers’ curricular decision-making with ChatGPT

Despite emerging research on Artificial Intelligence in mathematics education, studies on how secondary preservice mathematics teachers make curricular decisions when using Artificial Intelligence tools (e.g., ChatGPT) to generate mathematical tasks are underdeveloped. Building on prior research that shows how teachers consider factors related to students’ needs, valid mathematics disciplinary ideas, contextual and institutional factors, and their own characteristics, we unpack how these factors interacted when secondary preservice mathematics teachers reflected on their prompts used to generate mathematical tasks using ChatGPT and their evaluation of ChatGPT-generated tasks. We also examined the potentials and challenges teachers identified in using ChatGPT for generating tasks. Preservice mathematics teachers highlighted the need for adjusting the difficulty level of ChatGPT-generated tasks, expressing concerns that the tasks at times did not (a) appropriately address students’ comprehension, (b) align with given standards/goals, and (c) present mathematics ideas coherently. They also shared formulating right prompts to generate appropriately challenging tasks was more time-consuming than writing their own tasks. By presenting examples of the factors that secondary preservice mathematics teachers considered when evaluating ChatGPT-generated mathematical tasks, we suggest strategies to help teacher and educators use Artificial Intelligence tools more efficiently in their curricular decision-making. We discuss how teachers’ engagement with Artificial Intelligence in curating curricular resources repositions teachers' curricular-decision making.

Authors

Institutions

Publication Details

Journal
International Electronic Journal of Mathematics Education
Published
2026-11-16
DOI
https://doi.org/10.29333/iejme/19970
Primary Topic
Artificial Intelligence in Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Prompting, evaluating, and adapting AI-generated mathematical tasks: Secondary preservice teachers’ curricular decision-making with ChatGPT

Bima Sapkota, Lili Zhou
6 links
International Electronic Journal of Mathematics Education
Artificial Intelligence in Education
article

Prompting, evaluating, and adapting AI-generated mathematical tasks: Secondary preservice teachers’ curricular decision-making with ChatGPT

Bima Sapkota, Lili Zhou
article en

Abstract

Despite emerging research on Artificial Intelligence in mathematics education, studies on how secondary preservice mathematics teachers make curricular decisions when using Artificial Intelligence tools (e.g., ChatGPT) to generate mathematical tasks are underdeveloped. Building on prior research that shows how teachers consider factors related to students’ needs, valid mathematics disciplinary ideas, contextual and institutional factors, and their own characteristics, we unpack how these factors interacted when secondary preservice mathematics teachers reflected on their prompts used to generate mathematical tasks using ChatGPT and their evaluation of ChatGPT-generated tasks. We also examined the potentials and challenges teachers identified in using ChatGPT for generating tasks. Preservice mathematics teachers highlighted the need for adjusting the difficulty level of ChatGPT-generated tasks, expressing concerns that the tasks at times did not (a) appropriately address students’ comprehension, (b) align with given standards/goals, and (c) present mathematics ideas coherently. They also shared formulating right prompts to generate appropriately challenging tasks was more time-consuming than writing their own tasks. By presenting examples of the factors that secondary preservice mathematics teachers considered when evaluating ChatGPT-generated mathematical tasks, we suggest strategies to help teacher and educators use Artificial Intelligence tools more efficiently in their curricular decision-making. We discuss how teachers’ engagement with Artificial Intelligence in curating curricular resources repositions teachers' curricular-decision making.

International Electronic Journal of Mathematics EducationVol. 21(4)
University of Kentucky (US), California State University Los Angeles (US)
Quality education
Artificial Intelligence in Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon