MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Surana, Rohan, Li, Xintong, Yu, Sheldon, Shen, Yiran Jenny, Wang, Chuhan, Yu, Tong, Ammanabrolu, Prithviraj, Shang, Jingbo, McAuley, Julian, Wu, Junda
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!