The University of Southampton
University of Southampton Institutional Repository

Exploring the role of large language models in the scientific method: from hypothesis to discovery

Exploring the role of large language models in the scientific method: from hypothesis to discovery
Exploring the role of large language models in the scientific method: from hypothesis to discovery
We review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics.
3005-1460
Zhang, Yanbo
2571a7f9-8318-43be-8c2c-161a57c1c6bc
Khan, Sumeer A.
41b77ad4-67df-43b2-bf74-9c5f959fb6b4
Mahmud, Adnan
a9a0bc76-a94a-464c-a15c-575e18a2d28f
Yang, Huck
b254393c-2c81-4123-8291-e6f1a439f905
Lavin, Alexander
a0dadc06-c71b-46c4-a24d-6e307a0aa2ab
Levin, Michael
099b2594-e6ba-4d6f-bb3d-f0f53f22a4da
Frey, Jeremy G.
ba60c559-c4af-44f1-87e6-ce69819bf23f
Dunnmon, Jared
27884856-0fc1-4684-a88c-ae4a18933826
Evans, James
f29c0b01-7ff1-4bbc-868c-46027fc95d2c
Bundy, Alan
dc71d359-0869-4692-837b-d16979bdcf62
Dzeroski, Saso
912a54eb-4441-4c6f-9b98-3758f4aaabd3
Tegner, Jesper
9416c9ec-9adc-4432-aff3-4477c4f7b1e9
Zenil, Hector
5da6fe18-37e5-4b94-8c98-739a07023118
Zhang, Yanbo
2571a7f9-8318-43be-8c2c-161a57c1c6bc
Khan, Sumeer A.
41b77ad4-67df-43b2-bf74-9c5f959fb6b4
Mahmud, Adnan
a9a0bc76-a94a-464c-a15c-575e18a2d28f
Yang, Huck
b254393c-2c81-4123-8291-e6f1a439f905
Lavin, Alexander
a0dadc06-c71b-46c4-a24d-6e307a0aa2ab
Levin, Michael
099b2594-e6ba-4d6f-bb3d-f0f53f22a4da
Frey, Jeremy G.
ba60c559-c4af-44f1-87e6-ce69819bf23f
Dunnmon, Jared
27884856-0fc1-4684-a88c-ae4a18933826
Evans, James
f29c0b01-7ff1-4bbc-868c-46027fc95d2c
Bundy, Alan
dc71d359-0869-4692-837b-d16979bdcf62
Dzeroski, Saso
912a54eb-4441-4c6f-9b98-3758f4aaabd3
Tegner, Jesper
9416c9ec-9adc-4432-aff3-4477c4f7b1e9
Zenil, Hector
5da6fe18-37e5-4b94-8c98-739a07023118

Zhang, Yanbo, Khan, Sumeer A., Mahmud, Adnan, Yang, Huck, Lavin, Alexander, Levin, Michael, Frey, Jeremy G., Dunnmon, Jared, Evans, James, Bundy, Alan, Dzeroski, Saso, Tegner, Jesper and Zenil, Hector (2025) Exploring the role of large language models in the scientific method: from hypothesis to discovery. npj Artificial Intelligence, 1 (14), [14]. (doi:10.1038/s44387-025-00019-5).

Record type: Article

Abstract

We review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics.

Text
s44387-025-00019-5 (1) - Version of Record
Available under License Creative Commons Attribution.
Download (985kB)

More information

Accepted/In Press date: 23 June 2025
Published date: 5 August 2025

Identifiers

Local EPrints ID: 504087
URI: http://eprints.soton.ac.uk/id/eprint/504087
ISSN: 3005-1460
PURE UUID: 73e80065-943e-4c93-99c7-ac2d22817479
ORCID for Jeremy G. Frey: ORCID iD orcid.org/0000-0003-0842-4302

Catalogue record

Date deposited: 22 Aug 2025 17:00
Last modified: 23 Aug 2025 01:34

Export record

Altmetrics

Contributors

Author: Yanbo Zhang
Author: Sumeer A. Khan
Author: Adnan Mahmud
Author: Huck Yang
Author: Alexander Lavin
Author: Michael Levin
Author: Jeremy G. Frey ORCID iD
Author: Jared Dunnmon
Author: James Evans
Author: Alan Bundy
Author: Saso Dzeroski
Author: Jesper Tegner
Author: Hector Zenil

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×