Banishing LLM Hallucinations Requires Rethinking Generalization

Despite their powerful chat, coding, and reasoning abilities, Large Language Models (LLMs) frequently hallucinate. Conventional wisdom suggests that hallucinations are a consequence of a balance between creativity and factuality, which can be mitigated, but not eliminated, by grounding the LLM in ex...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Li, Johnny, Consul, Saksham, Zhou, Eda, Wong, James, Farooqui, Naila, Ye, Yuxin, Nithyashree Manohar, Zhuxiaona Wei, Wu, Tian, Echols, Ben, Zhou, Sharon, Diamos, Gregory
Format:	Artikel
Sprache:	eng
Schlagworte:	Hallucinations Large language models Mixtures Neural networks Random numbers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!