Every Part Matters: Integrity Verification of Scientific Figures Based on Multimodal Large Language Models

TL;DR

This paper introduces a new task and dataset for verifying the alignment of text and visual elements in scientific figures, utilizing multimodal large language models to improve accuracy and reasoning capabilities.

Contribution

It presents a novel task, Figure Integrity Verification, a large-scale dataset, and an innovative framework leveraging multimodal large language models for precise figure analysis.

Findings

Significant improvement over existing methods in text-figure alignment accuracy

Enhanced reasoning capabilities through analogical reasoning in figure verification

Framework effectively handles complex scientific figures for integrity verification

Abstract

This paper tackles a key issue in the interpretation of scientific figures: the fine-grained alignment of text and figures. It advances beyond prior research that primarily dealt with straightforward, data-driven visualizations such as bar and pie charts and only offered a basic understanding of diagrams through captioning and classification. We introduce a novel task, Figure Integrity Verification, designed to evaluate the precision of technologies in aligning textual knowledge with visual elements in scientific figures. To support this, we develop a semi-automated method for constructing a large-scale dataset, Figure-seg, specifically designed for this task. Additionally, we propose an innovative framework, Every Part Matters (EPM), which leverages Multimodal Large Language Models (MLLMs) to not only incrementally improve the alignment and verification of text-figure integrity but also enhance integrity through analogical reasoning. Our comprehensive experiments show that these innovations substantially improve upon existing methods, allowing for more precise and thorough analysis of complex scientific figures. This progress not only enhances our understanding of multimodal technologies but also stimulates further research and practical applications across fields requiring the accurate interpretation of complex visual data.