CV

Profile

I am currently completing my PhD in Digital Humanities at the University of Florence, where I also hold a Research Fellowship. My research focuses on computational pragmatics, semantic interpretation, and the use of Large Language Models for detecting and explaining implicit meaning, especially in political discourse.

Alongside my academic work, I am an AI Expert at FairyMinds and a member of Lablita (Laboratorio di linguistica italiana), led by Alessandro Panunzi.

Current Positions

Research Fellow, University of Florence
PhD Candidate in Digital Humanities, University of Florence
AI Expert, FairyMinds
Research Group Member, Lablita, University of Florence

Research Interests

Computational pragmatics and semantics: implicit meaning, irony, presuppositions, implicatures, and LLM-based pragmatic reasoning.
LLMs and evaluation: benchmark design, instruction tuning, explanation generation, and multimodal evaluation.
Text simplification and accessibility: automatic generation and simplification of technical, bureaucratic, and legal language.
Cognition and philosophy of semantics: how meaning is acquired, represented, and adapted in context.

Education

PhD in Digital Humanities, University of Florence
MA in Logic, Philosophy and History of Science, University of Florence, graduated with honors

Selected Publications

Teaching LLMs to unveil tendentious implicit contents of Italian political communication. Forthcoming in the Workshop on Cognitive Modeling and Computational Linguistics (CMCL).
Evaluating the abilities of LLMs and SpeechLMs in discovering implicit contents of Italian political speeches. Forthcoming in the Workshop on Natural Language Processing for Political Sciences (PoliticalNLP).
IMPOLS at EVALITA 2026: Overview of the IMPOLS Task. Proceedings of EVALITA 2026.
They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse. Findings of the Association for Computational Linguistics: ACL 2025.
“It’s a further exercise in futility”: implicit content detection and classification in Italian political discourse. A pilot study. AI-Linguistica, 2025.
Exploiting ChatGPT to simplify Italian bureaucratic and professional texts. AI-Linguistica, 2025.
Word classes and corpus linguistics. In Manual of Romance Word Classes, De Gruyter, 2024.

More details are available in the Publications section.

Talks and Conferences

Poster, Findings of ACL 2025, Vienna: They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse.
Talk, HuMaLa 2025, Granada: In my political ingenuity…: how LLMs detect and classify irony in Italian political discourse.
Invited Talk, Universidad Autónoma de Madrid: Challenges for LLMs: Dealing with presuppositions and implicatures.
Talk, Ai-ROM 2024, Technische Universität Dresden: “It’s a further exercise in futility”: implicit content detection and classification in Italian political discourse. A pilot study.
Poster, UnImplicit Workshop at EACL 2024, Malta.
Invited Talk, University of Pisa: Large Language Models and Prompt Engineering techniques.

More details are available in the Talks & Conferences section.

Visiting and Research Activities

Visiting period at Universidad Autónoma de Madrid (UAM) as a guest PhD student
Research visit at the MaiNLP Lab, Munich
Research stay with the Dialogue Modelling Group (DMG) at the Institute of Logic, Language and Computation (ILLC), Amsterdam
Organizing committee member for FLUI, University of Florence

Languages and Skills

Research methods: corpus linguistics, qualitative and quantitative analysis, benchmark design, annotation-driven evaluation
AI and NLP: Large Language Models, prompt engineering, instruction tuning, implicit content detection, text simplification
Languages: Italian, English