Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Zuhong, Ren, Daoyuan, Ran, Kai, Sun, Jing, Yu, Songlin, Bai, Xuefeng, Huang, Xiaotian, He, Haiyang, Pan, Pengxu, Fang, Ying, Li, Zhanglin, Li, Haipu, Yao, Jingjing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.18880
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918348705497088
author Lin, Zuhong
Ren, Daoyuan
Ran, Kai
Sun, Jing
Yu, Songlin
Bai, Xuefeng
Huang, Xiaotian
He, Haiyang
Pan, Pengxu
Fang, Ying
Li, Zhanglin
Li, Haipu
Yao, Jingjing
author_facet Lin, Zuhong
Ren, Daoyuan
Ran, Kai
Sun, Jing
Yu, Songlin
Bai, Xuefeng
Huang, Xiaotian
He, Haiyang
Pan, Pengxu
Fang, Ying
Li, Zhanglin
Li, Haipu
Yao, Jingjing
contents Accurately identifying the synthesis conditions of metal-organic frameworks (MOFs) is essential for guiding experimental design, yet remains challenging because relevant information in the literature is often scattered, inconsistent, and difficult to interpret. We present MOFh6, a large language model driven system that reads raw articles or crystal codes and converts them into standardized synthesis tables. It links related descriptions across paragraphs, unifies ligand abbreviations with full names, and outputs structured parameters ready for use. MOFh6 achieved 99% extraction accuracy, resolved 94.1% of abbreviation cases across five major publishers, and maintained a precision of 0.93 +/- 0.01. Processing a full text takes 9.6 s, locating synthesis descriptions 36 s, with 100 papers processed for USD 4.24. By replacing static database lookups with real-time extraction, MOFh6 reshapes MOF synthesis research, accelerating the conversion of literature knowledge into practical synthesis protocols and enabling scalable, data-driven materials discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18880
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reshaping MOFs text mining with a dynamic multi-agents framework of large language model
Lin, Zuhong
Ren, Daoyuan
Ran, Kai
Sun, Jing
Yu, Songlin
Bai, Xuefeng
Huang, Xiaotian
He, Haiyang
Pan, Pengxu
Fang, Ying
Li, Zhanglin
Li, Haipu
Yao, Jingjing
Artificial Intelligence
Materials Science
Computation and Language
Accurately identifying the synthesis conditions of metal-organic frameworks (MOFs) is essential for guiding experimental design, yet remains challenging because relevant information in the literature is often scattered, inconsistent, and difficult to interpret. We present MOFh6, a large language model driven system that reads raw articles or crystal codes and converts them into standardized synthesis tables. It links related descriptions across paragraphs, unifies ligand abbreviations with full names, and outputs structured parameters ready for use. MOFh6 achieved 99% extraction accuracy, resolved 94.1% of abbreviation cases across five major publishers, and maintained a precision of 0.93 +/- 0.01. Processing a full text takes 9.6 s, locating synthesis descriptions 36 s, with 100 papers processed for USD 4.24. By replacing static database lookups with real-time extraction, MOFh6 reshapes MOF synthesis research, accelerating the conversion of literature knowledge into practical synthesis protocols and enabling scalable, data-driven materials discovery.
title Reshaping MOFs text mining with a dynamic multi-agents framework of large language model
topic Artificial Intelligence
Materials Science
Computation and Language
url https://arxiv.org/abs/2504.18880