Download file (3.19MB)
Download as zip (2.63MB)

コレクション

引用

説明:

This study is dedicated to assessing the capabilities of large language models (LLMs) such as GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo in the extraction of structured information from scientific documents in materials science. To this end, we primarily focus on (i) a named entity recognition (NER) of studied materials and physical properties and (ii) a relation extraction (RE) between these entities. The performance of LLMs in executing these tasks is benchmarked against traditional models, BERT and rule-based approaches. As a typical result, GPT-4 and GPT-4-Turbo display remarkable reasoning and relationship extraction capabilities after being provided with merely a couple of examples.

権利情報:

• Creative Commons BY Attribution 4.0 International
  

キーワード: Large language models, benchmark, NER, TDM, evaluation, materials science

刊行年月日: 2024-12-31

出版者: Informa UK Limited

掲載誌:

• Science and Technology of Advanced Materials: Methods (ISSN: 27660400) vol. 4 issue. 1

研究助成金:

• Research and Development JPMXP1122715503

原稿種別: 出版者版 (Version of record)

MDR DOI:

公開URL: https://doi.org/10.1080/27660400.2024.2356506

関連資料:

その他の識別子:

連絡先:

更新時刻: 2024-10-24 16:30:23 +0900

MDRでの公開時刻: 2024-10-24 16:30:24 +0900