Online Self-Preferring Language Models

Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward model to provide feedback for on-policy sampling responses. Recently, offline methods that directly fit responses with b...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Zhai, Yuanzhao, Zhang, Zhuo, Xu, Kele, Peng, Hanyang, Yu, Yue, Feng, Dawei, Yang, Cheng, Ding, Bo, Wang, Huaimin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!