mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hu, Anwen, Shi, Yaya, Xu, Haiyang, Ye, Jiabo, Ye, Qinghao, Yan, Ming, Li, Chenliang, Qian, Qi, Zhang, Ji, Huang, Fei
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929203512868864
author Hu, Anwen
Shi, Yaya
Xu, Haiyang
Ye, Jiabo
Ye, Qinghao
Yan, Ming
Li, Chenliang
Qian, Qi
Zhang, Ji
Huang, Fei
author_facet Hu, Anwen
Shi, Yaya
Xu, Haiyang
Ye, Jiabo
Ye, Qinghao
Yan, Ming
Li, Chenliang
Qian, Qi
Zhang, Ji
Huang, Fei
contents Recently, the strong text creation ability of Large Language Models(LLMs) has given rise to many tools for assisting paper reading or even writing. However, the weak diagram analysis abilities of LLMs or Multimodal LLMs greatly limit their application scenarios, especially for scientific academic paper writing. In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the multi-modal diagram analysis ability of Multimodal LLMs. By parsing Latex source files of high-quality papers, we carefully build a multi-modal diagram understanding dataset M-Paper. By aligning diagrams in the paper with related paragraphs, we construct professional diagram analysis samples for training and evaluation. M-Paper is the first dataset to support joint comprehension of multiple scientific diagrams, including figures and tables in the format of images or Latex codes. Besides, to better align the copilot with the user's intention, we introduce the `outline' as the control signal, which could be directly given by the user or revised based on auto-generated ones. Comprehensive experiments with a state-of-the-art Mumtimodal LLM demonstrate that training on our dataset shows stronger scientific diagram understanding performance, including diagram captioning, diagram analysis, and outline recommendation. The dataset, code, and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/PaperOwl.
format Preprint
id arxiv_https___arxiv_org_abs_2311_18248
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model
Hu, Anwen
Shi, Yaya
Xu, Haiyang
Ye, Jiabo
Ye, Qinghao
Yan, Ming
Li, Chenliang
Qian, Qi
Zhang, Ji
Huang, Fei
Multimedia
Computation and Language
Recently, the strong text creation ability of Large Language Models(LLMs) has given rise to many tools for assisting paper reading or even writing. However, the weak diagram analysis abilities of LLMs or Multimodal LLMs greatly limit their application scenarios, especially for scientific academic paper writing. In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the multi-modal diagram analysis ability of Multimodal LLMs. By parsing Latex source files of high-quality papers, we carefully build a multi-modal diagram understanding dataset M-Paper. By aligning diagrams in the paper with related paragraphs, we construct professional diagram analysis samples for training and evaluation. M-Paper is the first dataset to support joint comprehension of multiple scientific diagrams, including figures and tables in the format of images or Latex codes. Besides, to better align the copilot with the user's intention, we introduce the `outline' as the control signal, which could be directly given by the user or revised based on auto-generated ones. Comprehensive experiments with a state-of-the-art Mumtimodal LLM demonstrate that training on our dataset shows stronger scientific diagram understanding performance, including diagram captioning, diagram analysis, and outline recommendation. The dataset, code, and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/PaperOwl.
title mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model
topic Multimedia
Computation and Language
url https://arxiv.org/abs/2311.18248