File Download

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

박양정

Park, Yang Jeong
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Can ChatGPT be used to generate scientific hypotheses?

Author(s)
Park, Yang JeongKaplan, DanielRen, ZhichuHsu, Chia-WeiLi, ChanghaoXu, HaoweiLi, SipeiLi, Ju
Issued Date
2024-05
DOI
10.1016/j.jmat.2023.08.007
URI
https://scholarworks.unist.ac.kr/handle/201301/91293
Fulltext
https://www.sciencedirect.com/science/article/pii/S2352847823001557?via%3Dihub
Citation
JOURNAL OF MATERIOMICS, v.10, no.3, pp.578 - 584
Abstract
We investigate whether large language models can perform the creative hypothesis generation that human researchers regularly do. While the error rate is high, generative AI seems to be able to effectively structure vast amounts of scientific knowledge and provide interesting and testable hypotheses. The future scientific enterprise may include synergistic efforts with a swarm of "hypothesis machines", challenged by automated experimentation and adversarial peer reviews. (c) 2023 The Authors. Published by Elsevier B.V. on behalf of The Chinese Ceramic Society. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Publisher
ELSEVIER
ISSN
2352-8478
Keyword (Author)
generative AIGPT-4large language modelsscientific hypothesis generation

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.