Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guan, Yifeng, Liu, Chuyi, Zhou, Dongzhan, Bai, Lei, Yin, Wan-jian, Li, Jingyuan, Su, Mao
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915819784503296
author Guan, Yifeng
Liu, Chuyi
Zhou, Dongzhan
Bai, Lei
Yin, Wan-jian
Li, Jingyuan
Su, Mao
author_facet Guan, Yifeng
Liu, Chuyi
Zhou, Dongzhan
Bai, Lei
Yin, Wan-jian
Li, Jingyuan
Su, Mao
contents Discovering interpretable physical laws from high-dimensional data is a fundamental challenge in scientific research. Traditional methods, such as symbolic regression, often produce complex, unphysical formulas when searching a vast space of possible forms. We introduce a framework that guides the search process by leveraging the embedded scientific knowledge of large language models, enabling efficient identification of physical laws in the data. We validate our approach by modeling key properties of perovskite materials. Our method mitigates the combinatorial explosion commonly encountered in traditional symbolic regression, reducing the effective search space by a factor of approximately $10^5$. A set of novel formulas for bulk modulus, band gap, and oxygen evolution reaction activity are identified, which not only provide meaningful physical insights but also outperform previous formulas in accuracy and simplicity.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22967
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression
Guan, Yifeng
Liu, Chuyi
Zhou, Dongzhan
Bai, Lei
Yin, Wan-jian
Li, Jingyuan
Su, Mao
Computational Physics
Artificial Intelligence
Discovering interpretable physical laws from high-dimensional data is a fundamental challenge in scientific research. Traditional methods, such as symbolic regression, often produce complex, unphysical formulas when searching a vast space of possible forms. We introduce a framework that guides the search process by leveraging the embedded scientific knowledge of large language models, enabling efficient identification of physical laws in the data. We validate our approach by modeling key properties of perovskite materials. Our method mitigates the combinatorial explosion commonly encountered in traditional symbolic regression, reducing the effective search space by a factor of approximately $10^5$. A set of novel formulas for bulk modulus, band gap, and oxygen evolution reaction activity are identified, which not only provide meaningful physical insights but also outperform previous formulas in accuracy and simplicity.
title Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression
topic Computational Physics
Artificial Intelligence
url https://arxiv.org/abs/2602.22967