Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents

Tagliolato Acquaviva d’Aragona, Paolo; Bordogna, Gloria; Babbini, Lorenza; Lotti, Alessandro; Minelli, Annalisa; Zilioli, Martina; Oggioni, Alessandro

doi:10.3390/app15105415

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents

by

Paolo Tagliolato Acquaviva d’Aragona

^1,*,†

,

Gloria Bordogna

^1,†

,

Lorenza Babbini

²

,

Alessandro Lotti

²

,

Annalisa Minelli

²

,

Martina Zilioli

¹

and

Alessandro Oggioni

¹

Institute for Remote Sensing of Environment (IREA), National Research Council (CNR), Via A. Corti 12, 20133 Milano, Italy

²

INFO/RAC UNEP/MAP c/o ISPRA, DG-SINA, Via Vitaliano Brancati 48, 00144 Roma, Italy

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Appl. Sci. 2025, 15(10), 5415; https://doi.org/10.3390/app15105415

Submission received: 4 April 2025 / Revised: 3 May 2025 / Accepted: 6 May 2025 / Published: 12 May 2025

(This article belongs to the Section Computing and Artificial Intelligence)

Download Versions Notes

Abstract

This contribution outlines the design of a Knowledge Hub of heterogeneous documents related to the UNEP/MAP Barcelona Convention system. The Knowledge Hub is intended to serve as a resource to assist public authorities and users with different backgrounds and needs in accessing information efficiently; users should be able to either formulate natural language queries or to navigate a knowledge graph that is automatically generated to find relevant documents. The ad hoc retrieval task and the Knowledge Hub creation are defined based on state-of-the-art Large Language Models (LLMs). Specifically, this contribution focuses on a user-evaluation experiment that tested publicly available pretrained foundation Large Language Models (LLMs) for retrieving a subset of documents with varying lengths and topics.

Keywords: knowledge hub; heterogeneous documents with highly variable length; foundation large language models; natural language queries; knowledge graph

Share and Cite

MDPI and ACS Style

Tagliolato Acquaviva d’Aragona, P.; Bordogna, G.; Babbini, L.; Lotti, A.; Minelli, A.; Zilioli, M.; Oggioni, A. Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents. Appl. Sci. 2025, 15, 5415. https://doi.org/10.3390/app15105415

AMA Style

Tagliolato Acquaviva d’Aragona P, Bordogna G, Babbini L, Lotti A, Minelli A, Zilioli M, Oggioni A. Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents. Applied Sciences. 2025; 15(10):5415. https://doi.org/10.3390/app15105415

Chicago/Turabian Style

Tagliolato Acquaviva d’Aragona, Paolo, Gloria Bordogna, Lorenza Babbini, Alessandro Lotti, Annalisa Minelli, Martina Zilioli, and Alessandro Oggioni. 2025. "Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents" Applied Sciences 15, no. 10: 5415. https://doi.org/10.3390/app15105415

APA Style

Tagliolato Acquaviva d’Aragona, P., Bordogna, G., Babbini, L., Lotti, A., Minelli, A., Zilioli, M., & Oggioni, A. (2025). Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents. Applied Sciences, 15(10), 5415. https://doi.org/10.3390/app15105415

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Testing Pretrained Large Language Models to Set up a Knowledge Hub of Heterogeneous Multisource Environmental Documents

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI