Federico Borazio Photo

Federico Borazio

PhD Student - Department of Enterprise Engineering / University of Rome Tor Vergata

Machine Learning NLP RAG for Question Answering Evaluation of Large Language Models Grounded Human Robot Interaction

Federico Borazio is a PhD candidate in the Data Science program at the University of Rome Tor Vergata , where he is a member of the SAG Art research group. His doctoral research is supervised by Roberto Basili and Danilo Croce.

His main research interests include Large Language Models fine-tuning and adaptation for downstream and knowledge-intensive tasks, question answering in the biomedical domain, retrieval-augmented generation, and multimodal dialogue systems. He has contributed to projects on LLM benchmarking, human-robot interaction, and AI applications for epidemic intelligence, publishing in venues such as ACL Findings, ECIR Industry Track, LREC-COLING Political NLP workshop, and the Italian Journal of Computational Linguistics.

He is also part of the CALAMITA Data and Evaluation Team, contributing to the benchmarking of Large Language Models on native Italian tasks.

In addition to his academic work, he collaborates with Reveal S.r.l., an industry partner focused on AI and NLP driven solutions.

Selected Publications

Reveal Industry Projects Collaboration

Matchmaking for Innovation - 2024/25
In collaboration with: Foundation Rome Technopole
Developed a semantic search engine to match technological and innovative challenges with academic research groups and industry projects.
Keywords: Python, Java, Transformer, Solr, Semantic Search, Knowledge Graphs, Word2Vec
Simple Knowledge Organization Systems for the Decommissioning of Nuclear Facilities - 2024
In collaboration with: International Atomic Energy Agency (IAEA)
Developed a semantic search engine for knowledge management in nuclear decommissioning.
Keywords: Python, Java, Transformer, Solr, Ontologies, Semantic Search, Knowledge Graphs, Word2Vec
Supporting Publications: [Borazio et al. 2025]
Italian Network of Epidemic Intelligence - 2023/24
In collaboration with: Italian Public Ministry of Health
Developed monitoring tools for pandemic events using NLP and machine learning for automatic analysis of online information.
Keywords: Python, Java, Transformer, Solr, Zero-Shot Learning, Web Scraping, Word2Vec
Supporting Publications: [Borazio et al. 2024, Croce et al. 2023]

Teaching Assistant

AY: 2024-25 and 2023-24 / Computer Engineering Master Degree

Contacts