Prompt engineering of GPT-4 for chemical research: what can/cannot be done?
-
- Kan Hatakeyama-Sato
- Tokyo Institute of Technology
-
- Naoki Yamane
- University of Tsukuba
-
- Yasuhiko Igarashi
- University of Tsukuba
-
- Yuta Nabae
- Tokyo Institute of Technology
-
- Teruaki Hayakawa
- Tokyo Institute of Technology
書誌事項
- 公開日
- 2023-10-09
- 資源種別
- journal article
- 権利情報
-
- http://creativecommons.org/licenses/by/4.0/
- DOI
-
- 10.1080/27660400.2023.2260300
- 10.26434/chemrxiv-2023-s1x5p
- 10.6084/m9.figshare.24270647.v1
- 10.6084/m9.figshare.24270647
- 公開者
- Informa UK Limited
説明
<jats:p>This paper evaluates the capabilities and limitations of the Generative Pre-trained Transformer 4 (GPT-4) in chemical research. Although GPT-4 exhibits remarkable proficiencies, it is evident that the quality of input data significantly affects its performance. We explore GPT-4's potential in chemical tasks, such as foundational chemistry knowledge, cheminformatics, data analysis, problem prediction, and proposal abilities. While the language model partially outperformed traditional methods, such as black-box optimization, it fell short against specialized algorithms, highlighting the need for their combined use. The paper shares the prompts given to GPT-4 and its responses, providing a resource for prompt engineering within the community, and concludes with a discussion on the future of chemical research using large language models.</jats:p>
収録刊行物
-
- Science and Technology of Advanced Materials: Methods
-
Science and Technology of Advanced Materials: Methods 3 (1), 2023-10-09
Informa UK Limited
関連未分類成果物
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1360584339777575936
-
- ISSN
- 27660400
-
- 資料種別
- journal article
-
- データソース種別
-
- Crossref
- KAKEN
- OpenAIRE
- IRDB