Work

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

Year: 2026
Type: article
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.
Language: English
Subfield: Education
Open Access status: diamond
OpenAlex ID: W7233987860
FWCI:
Cites: 33
Cited by:
Related to: 10