163959 20251113160752.0 doi 10.1016/j.procs.2025.09.193 sideral 146083 ART-2025-146083 eng de Curtò, J. Integrating Polyglot Persistence with Large Language Models for Scalable Social Network Applications 2025 Modern cloud applications, particularly those resembling professional social networks, demand data management systems capable of handling heterogeneous, highly interconnected data. Traditional relational databases are often inadequate for such dynamic environments. This paper proposes a polyglot persistence architecture that combines document, graph, and key–value data stores to address diverse data storage and query requirements. Moreover, by integrating Large Language Models (LLMs) as an intelligent query and analytics interface, the system can interpret natural language requests, generate structured queries across multiple data stores, and provide personalized insights. We discuss the architectural rationale, outline the integration of LLMs with multi-database systems, and propose future research directions. Access copy available to the general public Unrestricted info:eu-repo/semantics/openAccess by-nc-nd https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion de Zarzà, I. Universidad de Zaragoza (orcid)0000-0002-5844-7871 Calafate, Carlos T. 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 270 (2025), 733-743 Procedia computer science 1877-0509 GitHub https://github.com/drdecurto/polyglot_llm 724272 http://zaguan.unizar.es/record/163959/files/texto_completo.pdf Versión publicada 1939243 http://zaguan.unizar.es/record/163959/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:163959 articulos driver 2025-11-13-14:58:35 ARTICLE