Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models

About

The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce \textbf{MultiMath-7B}, a multimodal large language model that bridges the gap between math and vision. \textbf{MultiMath-7B} is trained through a four-stage process, focusing on vision-language alignment, visual and math instruction-tuning, and process-supervised reinforcement learning. We also construct a novel, diverse and comprehensive multimodal mathematical dataset, \textbf{MultiMath-300K}, which spans K-12 levels with image captions and step-wise solutions. MultiMath-7B achieves state-of-the-art (SOTA) performance among open-source models on existing multimodal mathematical benchmarks and also excels on text-only mathematical benchmarks. Our model and dataset are available at {\textcolor{blue}{\url{https://github.com/pengshuai-rin/MultiMath}}}.

Shuai Peng, Di Fu, Liangcai Gao, Xiuqin Zhong, Hongguang Fu, Zhi Tang• 2024

Related benchmarks

TaskDatasetResultRank
Visual Mathematical ReasoningMathVista
Accuracy50
278
Mathematical Multimodal ReasoningMathVerse
Accuracy26.9
221
Mathematical ReasoningMathVision
Accuracy16.3
144
Mathematical ReasoningMathVerse--
109
Mathematical ReasoningMathVista
Accuracy (All)50
43
Geometry Problem SolvingMathVista GPS
Accuracy66.8
38
Mathematical Problem SolvingMathVerse (testmini)
Accuracy27.7
28
Mathematical Problem SolvingMATH-Vision (test)
Accuracy16.3
26
Multimodal Mathematical ReasoningMathVerse mini (test)
T-Dominant Score34.8
26
Mathematical ReasoningMathVerse mini (test)
Accuracy34.8
26
Showing 10 of 20 rows

Other info

Follow for update