SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection

Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language model (SLM) classifier for initial detection, followed by a L...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-08
Hauptverfasser:	Hu, Mengya, Xu, Rui, Deren Lei, Li, Yaxi, Wang, Mingyu, Ching, Emily, Kamal, Eslam, Deng, Alex
Format:	Artikel
Sprache:	eng
Schlagworte:	Effectiveness Large language models Real time User experience
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!