Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	D'Oosterlinck, Karel, Xu, Winnie, Develder, Chris, Demeester, Thomas, Singh, Amanpreet, Potts, Christopher, Kiela, Douwe, Mehri, Shikib
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2408.06266