Harnessing Large Language Model to collect and analyze Metal-organic framework property dataset

TL;DR

This paper presents a systematic approach using large language models to extract and organize experimental Metal-Organic Framework data from literature, creating a comprehensive dataset to improve machine learning predictions in materials science.

Contribution

The study introduces a novel LLM-based method for large-scale extraction and structuring of MOF data from scientific articles, addressing data accessibility challenges.

Findings

Successfully compiled data from over 40,000 articles.

Experimental data improves machine learning prediction accuracy.

Method enhances data accessibility for MOF research.

Abstract

This research was focused on the efficient collection of experimental Metal-Organic Framework (MOF) data from scientific literature to address the challenges of accessing hard-to-find data and improving the quality of information available for machine learning studies in materials science. Utilizing a chain of advanced Large Language Models (LLMs), we developed a systematic approach to extract and organize MOF data into a structured format. Our methodology successfully compiled information from more than 40,000 research articles, creating a comprehensive and ready-to-use dataset. The findings highlight the significant advantage of incorporating experimental data over relying solely on simulated data for enhancing the accuracy of machine learning predictions in the field of MOF research.