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

Ernst Reinking and Marco Becker

EconStor Preprints from ZBW - Leibniz Information Centre for Economics

Abstract: 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.

Keywords: AI; RAG; artificial intelligence; Retrieval-Augmented Generation (search for similar items in EconPapers)
JEL-codes: M15 (search for similar items in EconPapers)
Date: 2024
New Economics Papers: this item is included in nep-cmp
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/285307/1/R ... nguage-models-EN.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:esprep:285307

Access Statistics for this paper

More papers in EconStor Preprints from ZBW - Leibniz Information Centre for Economics Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().