Large Language Models.


Journal

NEJM evidence
ISSN: 2766-5526
Titre abrégé: NEJM Evid
Pays: United States
ID NLM: 9918317485806676

Informations de publication

Date de publication:
Aug 2023
Historique:
medline: 6 2 2024
pubmed: 6 2 2024
entrez: 6 2 2024
Statut: ppublish

Résumé

Large Language ModelsIn the latest edition of Stats, STAT!, Fralick and colleagues explain the statistics behind large language models - used in chat bots like ChatGPT and Bard. While these new tools may seem remarkably intelligent, at their core they just assemble sentences based on statistics from large amounts of text.

Identifiants

pubmed: 38320147
doi: 10.1056/EVIDstat2300128
doi:

Types de publication

Journal Article Review

Langues

eng

Sous-ensembles de citation

IM

Pagination

EVIDstat2300128

Auteurs

Michael Fralick (M)

Division of General Internal Medicine, Sinai Health System, Toronto.

Chana A Sacks (CA)

Massachusetts General Hospital, Boston, Massachusetts.

Jeffrey M Drazen (JM)

Harvard Medical School, Boston, Massachusetts.

C Corey Hardin (CC)

Massachusetts General Hospital, Boston, Massachusetts.

Classifications MeSH