Large language model enhanced corpus of CO2 reduction electrocatalysts and synthesis procedures

• Published in: Scientific data Vol. 11; no. 1; pp. 347 - 12
• Main Authors: Chen, Xueqing, Gao, Yang, Wang, Ludi, Cui, Wenjuan, Huang, Jiamin, Du, Yi, Wang, Bin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 06.04.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/299/886; 639/301/299/890; Algorithms; Artificial intelligence; Carbon dioxide; Catalysis; Catalysts; Chatbots; Data Descriptor; Data mining; Datasets; Humanities and Social Sciences; Information processing; Language; Large language models; Machine learning; Metadata; multidisciplinary; Natural language processing; Science; Science (multidisciplinary); Scientists; Subject specialists
• ISSN: 2052-4463; 2052-4463
• DOI: 10.1038/s41597-024-03180-9

CO 2 electroreduction has garnered significant attention from both the academic and industrial communities. Extracting crucial information related to catalysts from domain literature can help scientists find new and effective electrocatalysts. Herein, we used various advanced machine learning, natural language processing techniques and large language models (LLMs) approaches to extract relevant information about the CO 2 electrocatalytic reduction process from scientific literature. By applying the extraction pipeline, we present an open-source corpus for electrocatalytic CO 2 reduction. The database contains two types of corpus: (1) the benchmark corpus, which is a collection of 6,985 records extracted from 1,081 publications by catalysis postgraduates; and (2) the extended corpus, which consists of content extracted from 5,941 documents using traditional NLP techniques and LLMs techniques. The Extended Corpus I and II contain 77,016 and 30,283 records, respectively. Furthermore, several domain literature fine-tuned LLMs were developed. Overall, this work will contribute to the exploration of new and effective electrocatalysts by leveraging information from domain literature using cutting-edge computer techniques.