KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zaifei, Chang, Hong, Hou, Ruibing, Shan, Shiguang, Chen, Xilin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911226728022016
author Yang, Zaifei
Chang, Hong
Hou, Ruibing
Shan, Shiguang
Chen, Xilin
author_facet Yang, Zaifei
Chang, Hong
Hou, Ruibing
Shan, Shiguang
Chen, Xilin
contents The molecular large language models have garnered widespread attention due to their promising potential on molecular applications. However, current molecular large language models face significant limitations in understanding molecules due to inadequate textual descriptions and suboptimal molecular representation strategies during pretraining. To address these challenges, we introduce KnowMol-100K, a large-scale dataset with 100K fine-grained molecular annotations across multiple levels, bridging the gap between molecules and textual descriptions. Additionally, we propose chemically-informative molecular representation, effectively addressing limitations in existing molecular representation strategies. Building upon these innovations, we develop KnowMol, a state-of-the-art multi-modal molecular large language model. Extensive experiments demonstrate that KnowMol achieves superior performance across molecular understanding and generation tasks. GitHub: https://github.com/yzf-code/KnowMol Huggingface: https://hf.co/datasets/yzf1102/KnowMol-100K
format Preprint
id arxiv_https___arxiv_org_abs_2510_19484
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
Yang, Zaifei
Chang, Hong
Hou, Ruibing
Shan, Shiguang
Chen, Xilin
Biomolecules
Artificial Intelligence
Machine Learning
The molecular large language models have garnered widespread attention due to their promising potential on molecular applications. However, current molecular large language models face significant limitations in understanding molecules due to inadequate textual descriptions and suboptimal molecular representation strategies during pretraining. To address these challenges, we introduce KnowMol-100K, a large-scale dataset with 100K fine-grained molecular annotations across multiple levels, bridging the gap between molecules and textual descriptions. Additionally, we propose chemically-informative molecular representation, effectively addressing limitations in existing molecular representation strategies. Building upon these innovations, we develop KnowMol, a state-of-the-art multi-modal molecular large language model. Extensive experiments demonstrate that KnowMol achieves superior performance across molecular understanding and generation tasks. GitHub: https://github.com/yzf-code/KnowMol Huggingface: https://hf.co/datasets/yzf1102/KnowMol-100K
title KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
topic Biomolecules
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.19484