The benefits, risks and bounds of personalizing the alignment of large language models to individuals
Crossref DOI link: https://doi.org/10.1038/s42256-024-00820-y
Published Online: 2024-04-23
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Kirk, Hannah Rose http://orcid.org/0000-0002-7419-5993
Vidgen, Bertie
Röttger, Paul
Hale, Scott A.
Text and Data Mining valid from 2024-04-23
Version of Record valid from 2024-04-23
Article History
Received: 26 May 2023
Accepted: 5 March 2024
First Online: 23 April 2024
Competing interests
: The authors declare no competing interests.