Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems offer a new paradigm for querying and retrieving information, making the resource recovery processes more efficient and accurate due to their ability to learn and generate responses based on vast knowledge databases. This paper aims to demonstrate these systems in a simplified form to initiate a scientific discussion on the possibility of integrating these technologies into archival and bibliographic resource retrieval systems, and more broadly, into cultural heritage management.

Intelligenza artificiale, Large Language Models (LLMs) e Retrieval-Augmented Generation (RAG). Nuovi strumenti per l’accesso alle risorse archivistiche e bibliografiche

Giorgia Di Marcantonio
2024-01-01

Abstract

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems offer a new paradigm for querying and retrieving information, making the resource recovery processes more efficient and accurate due to their ability to learn and generate responses based on vast knowledge databases. This paper aims to demonstrate these systems in a simplified form to initiate a scientific discussion on the possibility of integrating these technologies into archival and bibliographic resource retrieval systems, and more broadly, into cultural heritage management.
2024
Bibliothecae.it
Internazionale
https://bibliothecae.unibo.it/article/view/19982
File in questo prodotto:
File Dimensione Formato  
5.Saggi_Di+Marcantonio.pdf

accesso aperto

Descrizione: AI_LLM_RAG_Archives_contributo_DiMarcantonio
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 1.24 MB
Formato Adobe PDF
1.24 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11393/337670
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact