RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates preference pairs from two contrasting model outputs, one using a pos...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Yang, Kevin, Klein, Dan, Celikyilmaz, Asli, Peng, Nanyun, Tian, Yuandong
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!