Our new X account is live! Follow @wizwand_team for updates
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
189
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 ReasoningMathVista
Accuracy (All)50
23
Visual Mathematical ReasoningFlowVerse (test)
CoT Error (All)45.2
13
Mathematical ReasoningMathVerse-Plus Text Dominant 1.0 (test)
Accuracy35
12
Mathematical ReasoningMathVerse-Plus All 1.0 (test)
Accuracy24.6
12
Mathematical ReasoningMathVerse-Plus Text Lite 1.0 (test)
Accuracy25
12
Showing 10 of 13 rows

Other info

Follow for update