First Multi-Dimensional Evaluation of Flowchart Comprehension for Multimodal Large Language Models

TL;DR

This paper introduces FlowCE, a comprehensive evaluation framework for assessing multimodal large language models' abilities in understanding flowcharts across multiple dimensions, revealing current model limitations.

Contribution

The paper presents the first multi-dimensional evaluation method, FlowCE, specifically designed for flowchart-related tasks in multimodal large language models, filling a significant gap in assessment tools.

Findings

GPT-4o scores 56.63 on FlowCE

Open-source Phi-3-Vision scores 49.97

FlowCE highlights current model limitations in flowchart understanding

Abstract

With the development of Multimodal Large Language Models (MLLMs) technology, its general capabilities are increasingly powerful. To evaluate the various abilities of MLLMs, numerous evaluation systems have emerged. But now there is still a lack of a comprehensive method to evaluate MLLMs in the tasks related to flowcharts, which are very important in daily life and work. We propose the first comprehensive method, FlowCE, to assess MLLMs across various dimensions for tasks related to flowcharts. It encompasses evaluating MLLMs' abilities in Reasoning, Localization Recognition, Information Extraction, Logical Verification, and Summarization on flowcharts. However, we find that even the GPT4o model achieves only a score of 56.63. Among open-source models, Phi-3-Vision obtained the highest score of 49.97. We hope that FlowCE can contribute to future research on MLLMs for tasks based on flowcharts. \url{https://github.com/360AILABNLP/FlowCE}