Large language models and proprietary data - More accurate query results thanks to efficient data management and improved technical processes

Retrieval-Augmented Generation (RAG) synergistically combines the intrinsic knowledge of LLMs with the huge, dynamic databases of companies. Referencing the basic concept of a RAG ("Naive RAG"), this working paper identifies the critical factors of this cutting-edge architecture and gives hints for improvement. Finally, future paths for research and development are outlined.

MoreLess

Year of publication:	2024
Authors:	Reinking, Ernst ; Becker, Marco
Publisher:	Kiel, Hamburg : ZBW - Leibniz Information Centre for Economics
Subject:	AI \| RAG \| artificial intelligence \| Retrieval-Augmented Generation

More details

Series:	IUCF Working Paper
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	hdl:10419/285307 [Handle] RePEc:zbw:esprep:285307 [RePEc]
Classification:	M15 - IT Management
Source:	EconStor

Persistent link: https://www.econbiz.de/10014490230