In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-12
Hauptverfasser:	Amini, Afra, Ciaramita, Massimiliano
Format:	Artikel
Sprache:	eng
Schlagworte:	Classifiers Context Large language models Representations Robustness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!