LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery

TL;DR

This paper introduces LLM-Fusion, a multimodal fusion model utilizing large language models to integrate diverse material representations for improved property prediction in materials science.

Contribution

It presents a novel LLM-based architecture for multimodal data fusion, enhancing material property prediction accuracy over existing simple fusion methods.

Findings

Higher prediction accuracy than traditional methods

Effective integration of diverse material representations

Validated on multiple datasets and tasks

Abstract

Discovering materials with desirable properties in an efficient way remains a significant problem in materials science. Many studies have tackled this problem by using different sets of information available about the materials. Among them, multimodal approaches have been found to be promising because of their ability to combine different sources of information. However, fusion algorithms to date remain simple, lacking a mechanism to provide a rich representation of multiple modalities. This paper presents LLM-Fusion, a novel multimodal fusion model that leverages large language models (LLMs) to integrate diverse representations, such as SMILES, SELFIES, text descriptions, and molecular fingerprints, for accurate property prediction. Our approach introduces a flexible LLM-based architecture that supports multimodal input processing and enables material property prediction with higher accuracy than traditional methods. We validate our model on two datasets across five prediction tasks and demonstrate its effectiveness compared to unimodal and naive concatenation baselines.