Training Large Language Models to Reason in a Continuous Latent Space

Large language models (LLMs) are restricted to reason in the "language space", where they typically express the reasoning process with a chain-of-thought (CoT) to solve a complex reasoning problem. However, we argue that language space may not always be optimal for reasoning. For example,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Hao, Shibo, Sukhbaatar, Sainbayar, Su, DiJia, Li, Xian, Hu, Zhiting, Weston, Jason, Tian, Yuandong
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!