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

arXiv cs.AI / 4/25/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses a key bottleneck in metal-organic frameworks (MOFs): reliably scaling synthesis from lab discovery to industrial deployment despite fragmented know-how across reports.
It introduces ESU-MOF, a dataset mined from literature and coupled with a positive-unlabeled learning approach to train large language models for scalability prediction.
The proposed LLM method reportedly achieves 91.4% accuracy in predicting MOF synthesis scalability potential.
The authors position the approach as a way to support rapid, data-driven triage in industrial MOF discovery, helping prioritize candidates for scale-up efforts.

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.