Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

While large language models (LLMs) can answer many questions correctly, they can also hallucinate and give wrong answers. Wikidata, with its over 12 billion facts, can be used to ground LLMs to improve their factuality. This paper presents WikiWebQuestions, a high-quality question answering benchmar...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Xu, Silei, Liu, Shicheng, Culhane, Theo, Pertseva, Elizaveta, Wu, Meng-Hsi, Semnani, Sina J, Lam, Monica S
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!