Theoretical guarantees on the best-of-n alignment policy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Beirami, Ahmad, Agarwal, Alekh, Berant, Jonathan, D'Amour, Alexander, Eisenstein, Jacob, Nagpal, Chirag, Suresh, Ananda Theertha
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2401.01879