Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models

TL;DR

This paper presents ESU-MOF, a dataset and method using large language models to predict the scalability of MOF syntheses, aiding industrial deployment.

Contribution

It introduces a novel dataset and positive-unlabeled learning approach to accurately predict MOF synthesis scalability from literature data.

Findings

Achieved 91.4% accuracy in predicting MOF scale-up potential.

Enabled rapid, data-driven triage for industrial MOF discovery.

Demonstrated the effectiveness of LLMs in materials synthesis prediction.

Abstract

Scalable synthesis remains the gate between MOF discovery and industrial deployment, as scale-up know-how is fragmented across disparate reports. We introduce ESU-MOF, a literature-mined dataset and a positive-unlabeled learning strategy that fine-tunes large language models to predict scalability potential with 91.4% accuracy, enabling rapid data-driven triage for industrial MOF discovery.