DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models

TL;DR

DocGenome is a comprehensive, multi-modal scientific document benchmark with 500K annotated papers designed to evaluate and improve large language models' understanding of complex scientific data across various tasks.

Contribution

It introduces the first structured dataset covering all modalities and logical relationships in scientific documents, enabling advanced multi-task evaluation of large models.

Findings

Large models perform poorly on multi-page scientific document tasks

DocGenome improves evaluation of models' multi-modal understanding

Rigorous quality control ensures high dataset reliability

Abstract

Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data. Leveraging multi-modality data extracted from these documents and assessing large models' abilities to handle scientific document-oriented tasks is therefore meaningful. Despite promising advancements, large models still perform poorly on multi-page scientific document extraction and understanding tasks, and their capacity to process within-document data formats such as charts and equations remains under-explored. To address these issues, we present DocGenome, a structured document benchmark constructed by annotating 500K scientific documents from 153 disciplines in the arXiv open-access community, using our custom auto-labeling pipeline. DocGenome features four key characteristics: 1) Completeness: It is the first dataset to structure data from all modalities including 13 layout attributes along with their LaTeX source codes. 2) Logicality: It provides 6 logical relationships between different entities within each scientific document. 3) Diversity: It covers various document-oriented tasks, including document classification, visual grounding, document layout detection, document transformation, open-ended single-page QA and multi-page QA. 4) Correctness: It undergoes rigorous quality control checks conducted by a specialized team. We conduct extensive experiments to demonstrate the advantages of DocGenome and objectively evaluate the performance of large models on our benchmark.