Uncertainty Quantification for In-Context Learning of Large Language Models

In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM's response, such as hallucination, have also been actively discussed....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Chen, Ling, Zhao, Xujiang, Zhang, Xuchao, Cheng, Wei, Liu, Yanchi, Sun, Yiyou, Oishi, Mika, Osaki, Takao, Matsuda, Katsushi, Ji, Jie, Bai, Guangji, Zhao, Liang, Chen, Haifeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Context Decomposition Large language models Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!