Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barla, Adam, Nevali, Emanuele, Viano, Luca, Cevher, Volkan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!