Large Language Model-Driven Database for Thermoelectric Materials

TL;DR

This paper presents a large, curated database of thermoelectric materials extracted automatically from literature using large language models, facilitating data-driven discovery and optimization of these materials.

Contribution

The authors developed a comprehensive, open-access thermoelectric materials database using LLMs for automated data extraction, addressing manual curation challenges.

Findings

Created a database of 7,123 compounds with key thermoelectric properties

Automated data extraction improves efficiency and reliability of data collection

The database supports accelerated thermoelectric material research

Abstract

Thermoelectric materials provide a sustainable way to convert waste heat into electricity. However, data-driven discovery and optimization of these materials are challenging because of a lack of a reliable database. Here we developed a comprehensive database of 7,123 thermoelectric compounds, containing key information such as chemical composition, structural detail, seebeck coefficient, electrical and thermal conductivity, power factor, and figure of merit (ZT). We used the GPTArticleExtractor workflow, powered by large language models (LLM), to extract and curate data automatically from the scientific literature published in Elsevier journals. This process enabled the creation of a structured database that addresses the challenges of manual data collection. The open access database could stimulate data-driven research and advance thermoelectric material analysis and discovery.