A System and Benchmark for LLM-based Q&A on Heterogeneous Data

In many industrial settings, users wish to ask questions whose answers may be found in structured data sources such as a spreadsheets, databases, APIs, or combinations thereof. Often, the user doesn't know how to identify or access the right data source. This problem is compounded even further...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Fokoue, Achille, Jayaraman, Srideepika, Khabiri, Elham, Kephart, Jeffrey O, Li, Yingjie, Shah, Dhruv, Drissi, Youssef, Heath, Fenno F, Bhamidipaty, Anu, Tipu, Fateh A, Baseman, Robert J
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmarks Data retrieval Data sources Heterogeneity Large language models Natural language Questions Structured data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!