ChemDFM-X: Towards Large Multimodal Model for Chemistry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zihan, Chen, Bo, Li, Jingpiao, Chen, Lu, Wen, Liyang, Wang, Pengyu, Zhu, Zichen, Zhang, Danyang, Wan, Ziping, Li, Yansi, Dai, Zhongyang, Chen, Xin, Yu, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912174165721088
author Zhao, Zihan
Chen, Bo
Li, Jingpiao
Chen, Lu
Wen, Liyang
Wang, Pengyu
Zhu, Zichen
Zhang, Danyang
Wan, Ziping
Li, Yansi
Dai, Zhongyang
Chen, Xin
Yu, Kai
author_facet Zhao, Zihan
Chen, Bo
Li, Jingpiao
Chen, Lu
Wen, Liyang
Wang, Pengyu
Zhu, Zichen
Zhang, Danyang
Wan, Ziping
Li, Yansi
Dai, Zhongyang
Chen, Xin
Yu, Kai
contents Rapid developments of AI tools are expected to offer unprecedented assistance to the research of natural science including chemistry. However, neither existing unimodal task-specific specialist models nor emerging general large multimodal models (LMM) can cover the wide range of chemical data modality and task categories. To address the real demands of chemists, a cross-modal Chemical General Intelligence (CGI) system, which serves as a truly practical and useful research assistant utilizing the great potential of LMMs, is in great need. In this work, we introduce the first Cross-modal Dialogue Foundation Model for Chemistry (ChemDFM-X). Diverse multimodal data are generated from an initial modality by approximate calculations and task-specific model predictions. This strategy creates sufficient chemical training corpora, while significantly reducing excessive expense, resulting in an instruction-tuning dataset containing 7.6M data. After instruction finetuning, ChemDFM-X is evaluated on extensive experiments of different chemical tasks with various data modalities. The results demonstrate the capacity of ChemDFM-X for multimodal and inter-modal knowledge comprehension. ChemDFM-X marks a significant milestone toward aligning all modalities in chemistry, a step closer to CGI.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13194
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChemDFM-X: Towards Large Multimodal Model for Chemistry
Zhao, Zihan
Chen, Bo
Li, Jingpiao
Chen, Lu
Wen, Liyang
Wang, Pengyu
Zhu, Zichen
Zhang, Danyang
Wan, Ziping
Li, Yansi
Dai, Zhongyang
Chen, Xin
Yu, Kai
Machine Learning
Computation and Language
Multimedia
Rapid developments of AI tools are expected to offer unprecedented assistance to the research of natural science including chemistry. However, neither existing unimodal task-specific specialist models nor emerging general large multimodal models (LMM) can cover the wide range of chemical data modality and task categories. To address the real demands of chemists, a cross-modal Chemical General Intelligence (CGI) system, which serves as a truly practical and useful research assistant utilizing the great potential of LMMs, is in great need. In this work, we introduce the first Cross-modal Dialogue Foundation Model for Chemistry (ChemDFM-X). Diverse multimodal data are generated from an initial modality by approximate calculations and task-specific model predictions. This strategy creates sufficient chemical training corpora, while significantly reducing excessive expense, resulting in an instruction-tuning dataset containing 7.6M data. After instruction finetuning, ChemDFM-X is evaluated on extensive experiments of different chemical tasks with various data modalities. The results demonstrate the capacity of ChemDFM-X for multimodal and inter-modal knowledge comprehension. ChemDFM-X marks a significant milestone toward aligning all modalities in chemistry, a step closer to CGI.
title ChemDFM-X: Towards Large Multimodal Model for Chemistry
topic Machine Learning
Computation and Language
Multimedia
url https://arxiv.org/abs/2409.13194