Detecting Problematic Questions to Support Math Word Problem Design
Keywords: Problematic Question Detection, Question Design Support, Self-Optimization Prompting
Abstract: When designing math word problems, teachers must ensure the clarity and precision of the question to avoid multiple interpretations and unanswerable situations, thereby maintaining consistent grading standards and effectiveness. We address these issues to provide comprehensive support to teachers in creating clear, solvable, and formal math word problems. In this paper, we present MathError, a dataset of real-world math word problems annotated with error types to investigate the need for question correction. Our work explores how large language models (LLMs) can assist teachers in detecting problematic questions to support math word problem design in scenarios with limited data, simulating real-world conditions with minimal training samples. Preliminary results demonstrate the models' capabilities in detecting problematic questions and identify areas for further research and development in educational applications.
Supplementary Material: zip
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 758
Loading