Saved in:
Bibliographic Details
Main Authors: Perdikoulias, Christina, Vance, Chad, Watt, Stephen M.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02094
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915623429210112
author Perdikoulias, Christina
Vance, Chad
Watt, Stephen M.
author_facet Perdikoulias, Christina
Vance, Chad
Watt, Stephen M.
contents Artificial intelligence (AI) technology enables a range of enhancements in computer-aided instruction, from accelerating the creation of teaching materials to customizing learning paths based on learner outcomes. However, ensuring the mathematical accuracy and semantic integrity of generative AI output remains a significant challenge, particularly in Science, Technology, Engineering and Mathematics (STEM) disciplines. In this study, we explore the use of generative AI in which "hallucinations", typically viewed as undesirable inaccuracies, can instead serve a pedagogical purpose. Specifically, we investigate the generation of plausible but incorrect alternatives for multiple choice assessments, where credible distractors are essential for effective assessment design. We describe the Moebius platform for online instruction, with particular focus on its architecture for handling mathematical elements through specialized semantic packages that support dynamic, parameterized STEM content. We examine methods for crafting prompts that interact effectively with these mathematical semantics to guide the AI in generating high-quality multiple choice distractors. Finally, we demonstrate how this approach reduces the time and effort associated with creating robust teaching materials while maintaining academic rigor and assessment validity.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative AI for Multiple Choice STEM Assessments
Perdikoulias, Christina
Vance, Chad
Watt, Stephen M.
Computers and Society
Artificial intelligence (AI) technology enables a range of enhancements in computer-aided instruction, from accelerating the creation of teaching materials to customizing learning paths based on learner outcomes. However, ensuring the mathematical accuracy and semantic integrity of generative AI output remains a significant challenge, particularly in Science, Technology, Engineering and Mathematics (STEM) disciplines. In this study, we explore the use of generative AI in which "hallucinations", typically viewed as undesirable inaccuracies, can instead serve a pedagogical purpose. Specifically, we investigate the generation of plausible but incorrect alternatives for multiple choice assessments, where credible distractors are essential for effective assessment design. We describe the Moebius platform for online instruction, with particular focus on its architecture for handling mathematical elements through specialized semantic packages that support dynamic, parameterized STEM content. We examine methods for crafting prompts that interact effectively with these mathematical semantics to guide the AI in generating high-quality multiple choice distractors. Finally, we demonstrate how this approach reduces the time and effort associated with creating robust teaching materials while maintaining academic rigor and assessment validity.
title Generative AI for Multiple Choice STEM Assessments
topic Computers and Society
url https://arxiv.org/abs/2506.02094