Reward Generalization in RLHF: A Topological Perspective

Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been systematically characterized, nor have its alternatives been thoro...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Qiu, Tianyi, Zeng, Fanzhi, Ji, Jiaming, Yan, Dong, Wang, Kaile, Zhou, Jiayi, Han, Yang, Dai, Josef, Pan, Xuehai, Yang, Yaodong
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Discrete Mathematics Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!