Saved in:
Bibliographic Details
Main Authors: Hu, Chengxin, Li, Hao, Yuan, Yihe, Li, Jing, Tsang, Ivor
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.04708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929714016288768
author Hu, Chengxin
Li, Hao
Yuan, Yihe
Li, Jing
Tsang, Ivor
author_facet Hu, Chengxin
Li, Hao
Yuan, Yihe
Li, Jing
Tsang, Ivor
contents Following the milestones in large language models (LLMs) and multimodal models, we have seen a surge in applying LLMs to biochemical tasks. Leveraging graph features and molecular text representations, LLMs can tackle various tasks, such as predicting chemical reaction outcomes and describing molecular properties. However, most current work overlooks the *multi-level nature* of the graph modality, even though different chemistry tasks may benefit from different feature levels. In this work, we first study the effect of feature granularity and reveal that even reducing all GNN-generated feature tokens to a single one does not significantly impact model performance. We then investigate the effect of various graph feature levels and demonstrate that both the quality of LLM-generated molecules and model performance across different tasks depend on different graph feature levels. Therefore, we conclude with two key insights: (1) current molecular-related multimodal LLMs lack a comprehensive understanding of graph features, and (2) static processing is not sufficient for hierarchical graph feature. We share our findings in detail, with the hope of paving the way for the community to develop more advanced multimodal LLMs for incorporating molecular graphs.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04708
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Hierarchical Molecular Graph Representation in Multimodal LLMs
Hu, Chengxin
Li, Hao
Yuan, Yihe
Li, Jing
Tsang, Ivor
Machine Learning
Following the milestones in large language models (LLMs) and multimodal models, we have seen a surge in applying LLMs to biochemical tasks. Leveraging graph features and molecular text representations, LLMs can tackle various tasks, such as predicting chemical reaction outcomes and describing molecular properties. However, most current work overlooks the *multi-level nature* of the graph modality, even though different chemistry tasks may benefit from different feature levels. In this work, we first study the effect of feature granularity and reveal that even reducing all GNN-generated feature tokens to a single one does not significantly impact model performance. We then investigate the effect of various graph feature levels and demonstrate that both the quality of LLM-generated molecules and model performance across different tasks depend on different graph feature levels. Therefore, we conclude with two key insights: (1) current molecular-related multimodal LLMs lack a comprehensive understanding of graph features, and (2) static processing is not sufficient for hierarchical graph feature. We share our findings in detail, with the hope of paving the way for the community to develop more advanced multimodal LLMs for incorporating molecular graphs.
title Exploring Hierarchical Molecular Graph Representation in Multimodal LLMs
topic Machine Learning
url https://arxiv.org/abs/2411.04708