MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis

TL;DR

MindBench targets the gap in evaluating structured documents such as mind maps under Multimodal Large Language Models. It combines bilingual synthetic and real-world mind-map data with five parsing/understanding tasks and tailored metrics to assess text recognition, relationships, and spatial reasoning. Experiments reveal current OCR-free and domain-specialized models still struggle with high-resolution, long-structured graphs, but synthetic data and unified learning offer gains. This benchmark promises to accelerate research and practical advances in structured document analysis.

Abstract

Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex interactions between elements in structured documents such as mind maps and flowcharts. To address this issue, we introduce the new benchmark named MindBench, which not only includes meticulously constructed bilingual authentic or synthetic images, detailed annotations, evaluation metrics and baseline models, but also specifically designs five types of structured understanding and parsing tasks. These tasks include full parsing, partial parsing, position-related parsing, structured Visual Question Answering (VQA), and position-related VQA, covering key areas such as text recognition, spatial awareness, relationship discernment, and structured parsing. Extensive experimental results demonstrate the substantial potential and significant room for improvement in current models' ability to handle structured document information. We anticipate that the launch of MindBench will significantly advance research and application development in structured document analysis technology. MindBench is available at: https://miasanlei.github.io/MindBench.github.io/.

Figures (5)

• Figure 1: The illustration of unified structure learning of the MindBench benchmark.
• Figure 2: The illustration of data parsing.
• Figure 3: Resolution and token length distributions.
• Figure 4: A qualitative result of existing MLLMs in a zero-shot setting.
• Figure 5: A qualitative result of existing MLLMs tuned on the MindBench.