Hybrid Multimodal Generative Artificial Intelligence Approach for Mathematical Problem-Solving with Figures

Read full text Summarise with VIRAT
Authors: Sangsoo Lee, Jae-Hyun Baek, Jon-Lark Kim
Cited by: 0
References: 7

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Mathematical problem-solving with visual components remains a significant challenge for artificial intelligence (AI) systems.This is because conventional OCR pipelines often fail to extract critical structural cues such as axes, tick marks, and spatial relationships in diagrams or graphs.Despite recent advances in generative models, a cohesive framework that integrates visual perception with symbolic inference is still lacking.Therefore, this study proposes a lightweight hybrid pipeline that combines ColPali for vision-language understanding with open-source large language models (LLMs) such as LLaMA for symbolic reasoning.We evaluated our system on the MathVision dataset, leveraging its category-level statistics to measure the performance across diverse visual math tasks.Our method improves accuracy by up to 29.3% compared to standalone models, demonstrating the effectiveness of integrating visual structures into mathematical reasoning.

Fields of Study & Subjects

Handwritten Text Recognition Techniques Multimodal Machine Learning Applications Mathematics Computing and Information Processing

Publication details

Journal / source
International Journal of Fuzzy Logic and Intelligent Systems
Volume
26
Issue
1
Pages
1–9
Publication date
31 March 2026
Language
EN