Fine-tuning language models to find agreement among humans with diverse preferences

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a single "generic" user will confer more general al...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Bakker, Michiel A, Chadwick, Martin J, Sheahan, Hannah R, Tessler, Michael Henry, Campbell-Gillingham, Lucy, Balaguer, Jan, McAleese, Nat, Glaese, Amelia, Aslanides, John, Botvinick, Matthew M, Summerfield, Christopher
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!