DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: She, Shuaijie, Bao, Yu, Lu, Yu, Xu, Lu, Li, Tao, Zhu, Wenhao, Huang, Shujian, Cheng, Shanbo, Lu, Lu, Wang, Yuxuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!