GPT-Assisted Learning of Structure–Property Relationships by Graph Neural Networks: Application to Rare-Earth-Doped Phosphors

Zhang, Xiang; Zhou, Zichun; Ming, Chen; Sun, Yi-Yang

doi:10.1021/acs.jpclett.3c02848

Cited by 3 publications

(2 citation statements)

References 53 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent six months (2023.8-2024.1), the LLMs have been applied in materials science. [15][16][17][18][19][20][21][22][23][24][25][26][27][28] One of the efforts is to use LLMs, especially GPT-3.5 and GPT-4, to generate datasets. For example, Yang Jeong Park et al [15] generated 1.5 million materials narratives using Chat-GPT.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Literature classification and its applications in condensed matter physics and materials science by natural language processing

Wu 吴,

Zhu 朱,

Tu 涂

et al. 2024

Chinese Phys. B

View full text Add to dashboard Cite

The exponential growth of literature is constraining researchers’ access to comprehensive information in related fields. While natural language processing (NLP) may offer an effective solution to literature classification, it remains hindered by the lack of labelled dataset. In this article, we introduce a novel method for generating literature classification models through semi-supervised learning, which can generate labelled dataset iteratively with limited human input. We apply this method to train NLP models for classifying literatures related with several research directions, namely battery, superconductor, topological material, and artificial intelligence (AI) in materials science. The trained NLP ‘battery’ model applied on a larger dataset different from the training and testing dataset can achieve F1 score of 0.738, which indicates the accuracy and reliability of this scheme. Furthermore, our approach demonstrates that even with insufficient data, the not-well-trained model at first few cycles can identify the relationships among different research fields and facilitate the discovery and understanding of interdisciplinary directions.

show abstract

Section: Introductionmentioning

confidence: 99%

“…For example, Yang Jeong Park et al [15] generated 1.5 million materials narratives using Chat-GPT. Samuel J. Yang et al [16] generated extra DFT data using GPT-4 and Xiang Zhang et al [17] did for phosphors data. Another way is to pretrain or fine-tune the LLMs for differ-ent tasks.…”

Section: Introductionmentioning

confidence: 99%

Literature classification and its applications in condensed matter physics and materials science by natural language processing

Wu 吴,

Zhu 朱,

Tu 涂

et al. 2024

Chinese Phys. B

View full text Add to dashboard Cite

show abstract

Large‐Language‐Model‐Based AI Agent for Organic Semiconductor Device Research

Zhang,

Hu,

Yan

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

Large language models (LLMs) have attracted widespread attention recently, however, their application in specialized scientific fields still requires deep adaptation. In this work, we designed an artificial intelligence (AI) agent for organic field effect transistors (OFETs) by integrating the GPT‐4 model with well‐trained machine learning (ML) algorithms. It can efficiently extract the experimental parameters of OFETs from scientific literature and reshape them into a structured database, achieving precision and recall rates both exceeding 92%. Combined with well‐trained ML models, this AI agent can further provide targeted guidance and suggestions for device design. With prompt engineering and human‐in‐loop strategies, the agent extracted sufficient information of 709 OFETs from 277 research articles across different publishers and gathered them into a standardized database containing more than 10000 device parameters. Using this database, we trained a ML model based on XGBoost for device performance judgment. Combined with the interpretation of the high‐precision model, the agent has provided a feasible optimization scheme that has tripled the charge transport properties of DP‐DTT OFETs. Our work is an effective practice of LLMs in the field of organic optoelectronic devices and expands the research paradigm of organic optoelectronic materials and devices.This article is protected by copyright. All rights reserved

show abstract