Saved in:
Bibliographic Details
Main Authors: Yamamoto, Ryoma, Takahashi, Akira, Terayama, Kei, Kumagai, Yu, Oba, Fumiyasu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.26060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908916775911424
author Yamamoto, Ryoma
Takahashi, Akira
Terayama, Kei
Kumagai, Yu
Oba, Fumiyasu
author_facet Yamamoto, Ryoma
Takahashi, Akira
Terayama, Kei
Kumagai, Yu
Oba, Fumiyasu
contents Large language models (LLMs) exhibit substantial potential across diverse scientific disciplines, including materials science. A property prediction framework, ZEBRA-Prop (Zero-Shot Embedding-Based Rapid and Accessible Regression Model for Materials Properties), is presented here as an extension of LLM-Prop. In contrast to LLM-Prop, which requires task-specific fine-tuning of the LLM, ZEBRA-Prop eliminates fine-tuning, thereby reducing computational cost and enabling rapid model training. The framework employs MatTPUSciBERT, an LLM specialized for materials science, to enhance predictive capability. Multiple textual embeddings are incorporated through a learnable weighting mechanism, which alleviates the context-length constraints inherent in LLM-Prop and facilitates effective integration of diverse textual representations. Evaluation is conducted using two datasets: the TextEdge dataset (approximately 140,000 entries) and an in-house dataset (approximately 2,000 entries) derived from the Materials Project database, with physical properties obtained from first-principles calculations. The predictive performance of ZEBRA-Prop is close to that of LLM-Prop, while the training time is reduced by approximately 95%. The performance improvements are attributable to three principal factors: domain-specific LLM utilization, diversified textual descriptions, and systematic text preprocessing. ZEBRA-Prop constitutes a scalable and computationally efficient framework for materials property prediction and supports accelerated materials discovery, particularly under limited computational resources.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26060
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ZEBRA-Prop: A Zero-Shot Embedding-Based Rapid and Accessible Regression Model for Materials Properties
Yamamoto, Ryoma
Takahashi, Akira
Terayama, Kei
Kumagai, Yu
Oba, Fumiyasu
Materials Science
Large language models (LLMs) exhibit substantial potential across diverse scientific disciplines, including materials science. A property prediction framework, ZEBRA-Prop (Zero-Shot Embedding-Based Rapid and Accessible Regression Model for Materials Properties), is presented here as an extension of LLM-Prop. In contrast to LLM-Prop, which requires task-specific fine-tuning of the LLM, ZEBRA-Prop eliminates fine-tuning, thereby reducing computational cost and enabling rapid model training. The framework employs MatTPUSciBERT, an LLM specialized for materials science, to enhance predictive capability. Multiple textual embeddings are incorporated through a learnable weighting mechanism, which alleviates the context-length constraints inherent in LLM-Prop and facilitates effective integration of diverse textual representations. Evaluation is conducted using two datasets: the TextEdge dataset (approximately 140,000 entries) and an in-house dataset (approximately 2,000 entries) derived from the Materials Project database, with physical properties obtained from first-principles calculations. The predictive performance of ZEBRA-Prop is close to that of LLM-Prop, while the training time is reduced by approximately 95%. The performance improvements are attributable to three principal factors: domain-specific LLM utilization, diversified textual descriptions, and systematic text preprocessing. ZEBRA-Prop constitutes a scalable and computationally efficient framework for materials property prediction and supports accelerated materials discovery, particularly under limited computational resources.
title ZEBRA-Prop: A Zero-Shot Embedding-Based Rapid and Accessible Regression Model for Materials Properties
topic Materials Science
url https://arxiv.org/abs/2603.26060