English

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

Computer Vision and Pattern Recognition 2024-09-12 v2

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.

Keywords

Cite

@article{arxiv.2406.11633,
  title  = {DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models},
  author = {Renqiu Xia and Song Mao and Xiangchao Yan and Hongbin Zhou and Bo Zhang and Haoyang Peng and Jiahao Pi and Daocheng Fu and Wenjie Wu and Hancheng Ye and Shiyang Feng and Bin Wang and Chao Xu and Conghui He and Pinlong Cai and Min Dou and Botian Shi and Sheng Zhou and Yongwei Wang and Bin Wang and Junchi Yan and Fei Wu and Yu Qiao},
  journal= {arXiv preprint arXiv:2406.11633},
  year   = {2024}
}

Comments

Homepage of DocGenome: https://unimodal4reasoning.github.io/DocGenome_page 22 pages, 11 figures

R2 v1 2026-06-28T17:08:47.607Z