C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired fina...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Kang, Yu, Sun, Xianghui, Chen, Liangyu, Zou, Wei
Format:	Artikel
Sprache:	eng
Schlagworte:	Compressing Effectiveness Large language models Reasoning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!