Large language model-enabled automated data extraction for concrete materials informatics

TL;DR

This paper presents a large language model-based pipeline that automates the extraction of detailed concrete materials data from scientific literature, significantly expanding accessible datasets for materials informatics.

Contribution

It introduces a generalizable LLM-powered method for extracting structured materials data, achieving high accuracy and creating the largest open database for concrete materials.

Findings

Achieved an F1 score of up to 0.97 for data extraction.

Extracted nearly 9,000 records from over 27,000 publications in one hour.

Demonstrated the pipeline's adaptability to other materials domains.

Abstract

The promise of data-driven materials discovery remains constrained by the scarcity of large, high-quality, and accessible experimental datasets. Here, we introduce a generalizable large language model (LLM)-powered pipeline for automated extraction and structuring of materials data from unstructured scientific literature, using concrete materials as a representative and particularly challenging example. The pipeline exhibits robust performance across a broad range of LLMs and achieves an $F_1$ score of up to 0.97 for diverse composition--process--property attributes. Within one hour, it extracts nearly 9,000 high-quality records with over 100 attributes screened from more than 27,000 publications, enabling the construction of the largest open laboratory database for blended cement concrete. Machine learning analyses underscore the importance of large, diverse, and information-rich datasets for enhancing both in-distribution accuracy and out-of-distribution generalization to unseen materials. The proposed pipeline is readily adaptable to other materials domains and accelerates the development of scalable data infrastructures for materials informatics.