Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thought not only ac...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Liu, Ruibo, Jia, Chenyan, Zhang, Ge, Zhuang, Ziyu, Liu, Tony X, Vosoughi, Soroush
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computers and Society
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!