I am a postdoctoral researcher at IDSIA (Dalle Molle Institute for Artificial Intelligence), affiliated with SUPSI in Lugano, Switzerland. I completed my PhD in Language Sciences in the LLF and Lattice labs in December 2024, under the supervision of Marie Candito and Pascal Amsili. My research sits at the intersection of theoretical linguistics and natural language processing, focusing on how linguistic theory can inform and improve neural language models. I approach computational linguistics as a branch of language sciences, where computational methods serve to interrogate and illuminate linguistic theories.

Research Interests

My work explores the relationship between linguistic theory and language processing in neural models, with particular focus on:

• Negation in language models: How pretrained language models encode and process negation, including semantic constraints and compositional meaning
• Hallucination detection: Identifying and mitigating factual errors in RAG (Retrieval-Augmented Generation) systems
• Multilingual capabilities: Understanding how language family relationships influence LLM performance across languages
• Model interpretability: Probing neural representations to understand how linguistic phenomena are encoded

Current position

Postdoctoral Researcher (February 2025 - Present) IDSIA - Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland Supervisor: Fabio Rinaldi