Retrospective Learning from Interactions

Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the user is likely to signal it by rephrasing the request, expressing frustration, or pivoting to an alternative task. Such s...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chen, Zizhao, Gul, Mustafa Omer, Chen, Yiwei, Geng, Gloria, Wu, Anne, Artzi, Yoav
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!