# MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMs

arXiv: https://arxiv.org/abs/2503.04291 · HTML: https://mlsanity.com/paper/2503.04291/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought](https://mlsanity.com/paper/2405.06705/) (2024)
- [Large Language Models as Partners in Student Essay Evaluation](https://mlsanity.com/paper/2405.18632/) (2024)

## Built on by (most cited first, 1 of 1)

- [VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions](https://mlsanity.com/paper/2510.22798/) (2025)

## Abstract (arXiv)

We propose a novel system, MathMistake Checker, designed to automate step-by-step mistake finding in mathematical problems with lengthy answers through a two-stage process. The system aims to simplify grading, increase efficiency, and enhance learning experiences from a pedagogical perspective. It integrates advanced technologies, including computer vision and the chain-of-thought capabilities of the latest large language models (LLMs). Our system supports open-ended grading without reference answers and promotes personalized learning by providing targeted feedback. We demonstrate its effectiveness across various types of math problems, such as calculation and word problems.