Likelihood as a Performance Gauge for Retrieval-Augmented Generation

Recent work finds that retrieval-augmented generation with large language models is prone to be influenced by the order of retrieved documents in the context. However, the lack of in-depth analysis limits the use of this phenomenon for prompt engineering in practice. In this study, we posit that lik...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-11
Hauptverfasser:	Liu, Tianyu, Jirui Qi, He, Paul, Bisazza, Arianna, Sachan, Mrinmaya, Cotterell, Ryan
Format:	Artikel
Sprache:	eng
Schlagworte:	Context Effectiveness Large language models Prompt engineering Questions Retrieval
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!