MaterialBrain: High-Performance Material Synthesis Extraction via Human–AI-Curated Few-Shot Large Language Models
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.5c02299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Yi Yang und 17 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Beihang University, Beijing 100191, China. Hauptthemen laut MEDLINE: Artificial Intelligence, Metal-Organic Frameworks. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, National Social Science Fund of China.
Abstract (Originalsprache)
The extraction of the metal-organic framework synthesis route from the literature has been crucial for the rational MOFs design with desirable functionality. The recent advent of large language models (LLMs) provides a disruptive new solution to this long-standing problem. While the latest research on chemical data extraction mostly adopts zero-shot LLMs lacking specialized material knowledge or fine-tuned LLMs inducing high cost and inflexibility in our scenario, we introduce in this work the MaterialBrain pipeline that optimizes the few-shot LLMs in-context learning technique to accurately extract synthesis routes and design high-performance materials. First, a batch-epoch-iteration-based human-AI data curation approach is proposed to optimize both the quantity and quality of annotation database for the synthesis extraction task, which are pivotal to MaterialBrain's performance. Second, an information retrieval algorithm is applied to pick and quantify a few-shot demonstrations from the annotation database for each extraction. Over three data sets randomly sampled from nearly 90,000 well-defined MOFs, we conduct triple evaluations to validate our pipeline. The synthesis extraction, structure inference, and material design performance of MaterialBrain significantly outplay zero-shot LLMs and baseline methods. The specific surface area of the lab-synthesized material guided by LLMs surpasses that of 99.2% of MOFs of the same class reported in the literature.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science, Beihang University, Beijing 100191, China.
- School of Materials Science & Engineering, University of Science and Technology Beijing, Beijing 100083, China.
- Westlake University, Hangzhou 310030, China.
ORCID-Profile: Yi Yang, Siyu Wu, Rui Wang, Hongyi Gao, Ge Wang
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- National Social Science Fund of China
- State Key Laboratory of Complex and Critical Software Environment
Zitieren
APA
Yang, Y., Liu, Z., Wu, W., Zhang, Y., Zhang, H., Lin, J., Wu, S., Chen, Z., Sun, Y., Li, R., Wang, N., Wang, R., Liu, Z., Tan, H., Shi, L., Zhang, Y., Gao, H., & Wang, G. (2026). MaterialBrain: High-Performance Material Synthesis Extraction via Human–AI-Curated Few-Shot Large Language Models. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.5c02299
Vancouver
Yang Y, Liu Z, Wu W, Zhang Y, Zhang H, Lin J, et al. MaterialBrain: High-Performance Material Synthesis Extraction via Human–AI-Curated Few-Shot Large Language Models. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.5c02299
BibTeX
@article{Yang2026,
author = {Yang, Yi and Liu, Zhimeng and Wu, Weize and Zhang, Yuyang and Zhang, Hongbo and Lin, Jing and Wu, Siyu and Chen, Zihan and Sun, Ye and Li, Ruiming and Wang, Nan and Wang, Rui and Liu, Zipeng and Tan, Huobin and Shi, Lei and Zhang, Yue and Gao, Hongyi and Wang, Ge},
title = {MaterialBrain: High-Performance Material Synthesis Extraction via Human–AI-Curated Few-Shot Large Language Models},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.5c02299}
}
EUVIMED