Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design

ABSTRACT The design of sustainable materials requires access to materials performance and sustainability data from literature corpus in an organized, structured, and automated manner. Large language models (LLMs) have been explored for materials data extraction from the literature, yet often suffer from limited accuracy or narrow scope. Here, we present an LLM‐based pipeline for accurate information extraction from high‐entropy (multicomponent) alloy (HEA) literature. The approach produces two databases with 37,711 and 148,069 entries: one from text, capturing alloy compositions, processing conditions, characterization methods, and properties; and another from tables, containing property names, values, and units. Using prompt engineering and retrieval‐augmented generation, the pipeline improves materials‐domain sensitivity and achieves F1‐scores of 0.83 for text and 0.88 for tables, surpassing or matching existing approaches. Application of the pipeline to over 10,000 articles yields the largest publicly available multicomponent alloy database and reveals compositional and processing‐property trends. The database is further employed for sustainability‐aware materials selection in three application domains, i.e., lightweighting, soft magnetic, and corrosion‐resistant, identifying multicomponent alloy candidates with more sustainable production while maintaining or exceeding benchmark performance. The pipeline developed can be easily generalized to other classes of materials, supporting development of comprehensive, accurate, and usable databases for sustainable materials design.