Inverse Materials Design by Large Language Model-Assisted Generative Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hao, Yun, Fan, Che, Ye, Beilin, Lu, Wenhao, Lu, Zhen, Zhao, Peilin, Gao, Zhifeng, Wu, Qingyao, Liu, Yanhui, Wen, Tongqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910843868807168
author Hao, Yun
Fan, Che
Ye, Beilin
Lu, Wenhao
Lu, Zhen
Zhao, Peilin
Gao, Zhifeng
Wu, Qingyao
Liu, Yanhui
Wen, Tongqi
author_facet Hao, Yun
Fan, Che
Ye, Beilin
Lu, Wenhao
Lu, Zhen
Zhao, Peilin
Gao, Zhifeng
Wu, Qingyao
Liu, Yanhui
Wen, Tongqi
contents Deep generative models hold great promise for inverse materials design, yet their efficiency and accuracy remain constrained by data scarcity and model architecture. Here, we introduce AlloyGAN, a closed-loop framework that integrates Large Language Model (LLM)-assisted text mining with Conditional Generative Adversarial Networks (CGANs) to enhance data diversity and improve inverse design. Taking alloy discovery as a case study, AlloyGAN systematically refines material candidates through iterative screening and experimental validation. For metallic glasses, the framework predicts thermodynamic properties with discrepancies of less than 8% from experiments, demonstrating its robustness. By bridging generative AI with domain knowledge and validation workflows, AlloyGAN offers a scalable approach to accelerate the discovery of materials with tailored properties, paving the way for broader applications in materials science.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18127
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inverse Materials Design by Large Language Model-Assisted Generative Framework
Hao, Yun
Fan, Che
Ye, Beilin
Lu, Wenhao
Lu, Zhen
Zhao, Peilin
Gao, Zhifeng
Wu, Qingyao
Liu, Yanhui
Wen, Tongqi
Materials Science
Machine Learning
Deep generative models hold great promise for inverse materials design, yet their efficiency and accuracy remain constrained by data scarcity and model architecture. Here, we introduce AlloyGAN, a closed-loop framework that integrates Large Language Model (LLM)-assisted text mining with Conditional Generative Adversarial Networks (CGANs) to enhance data diversity and improve inverse design. Taking alloy discovery as a case study, AlloyGAN systematically refines material candidates through iterative screening and experimental validation. For metallic glasses, the framework predicts thermodynamic properties with discrepancies of less than 8% from experiments, demonstrating its robustness. By bridging generative AI with domain knowledge and validation workflows, AlloyGAN offers a scalable approach to accelerate the discovery of materials with tailored properties, paving the way for broader applications in materials science.
title Inverse Materials Design by Large Language Model-Assisted Generative Framework
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2502.18127