LLaMo: Large Language Model-based Molecular Graph Assistant

TL;DR

LLaMo is a novel large language model-based molecular graph assistant that integrates graph and language modalities for diverse molecular understanding tasks, leveraging instruction tuning and a multi-level graph projector.

Contribution

It introduces a multi-level graph projector and molecular graph instruction data for end-to-end training of a molecular graph-language model, enhancing molecular understanding capabilities.

Findings

LLaMo outperforms existing models on molecular description and property prediction tasks.

The multi-level graph projector effectively bridges graph and language modalities.

Instruction tuning improves generalization across molecular tasks.

Abstract

Large Language Models (LLMs) have demonstrated remarkable generalization and instruction-following capabilities with instruction tuning. The advancements in LLMs and instruction tuning have led to the development of Large Vision-Language Models (LVLMs). However, the competency of the LLMs and instruction tuning have been less explored in the molecular domain. Thus, we propose LLaMo: Large Language Model-based Molecular graph assistant, which is an end-to-end trained large molecular graph-language model. To bridge the discrepancy between the language and graph modalities, we present the multi-level graph projector that transforms graph representations into graph tokens by abstracting the output representations of each GNN layer and motif representations with the cross-attention mechanism. We also introduce machine-generated molecular graph instruction data to instruction-tune the large molecular graph-language model for general-purpose molecule and language understanding. Our extensive experiments demonstrate that LLaMo shows the best performance on diverse tasks, such as molecular description generation, property prediction, and IUPAC name prediction. The code of LLaMo is available at https://github.com/mlvlab/LLaMo.