I am a PostDoc Researcher at the Centre for Data Futures, King's College London. I previously was a Ph.D. Student and Research Associate at Politecnico di Torino and 2x Visiting Researcher at Nokia Bell Labs 🎓
My main research interests include Trustworthy AI, Fairness, Explainable Artificial Intelligence, and Natural Language Processing
-
I’m currently working on:
- Uncertainty in Large Language Models
- Participatory Artificial Intelligence
- NLP for stereotypes detection and inclusive language
-
I previously worked on:
- Bias mitigation in NLP classifiers
- Concept Drift detection in NLP classifiers
- NLP solutions to foster Inclusive Language in Italian
- Explainability in NLP and Computer Vision
I’m looking to collaborate on Trustworthy AI and NLP-related topics, including but not limited to:
- Bias and Fairness in NLP
- Large Language Models (LLMs)
- Uncertainty in LLMs
- Participatory AI
- Explainable AI
- Concept Drift
📫 How to reach me: send me an email
-
Unsupervised Concept Drift Detection From Deep Learning Representations in Real-Time
IEEE Transactions on Knowledge and Data Engineering (2025) 🔗 [paper] • [code]
→ Unsupervised framework for detecting, characterizing, and explaining drift in deep models on unstructured data -
Towards AI-Assisted Inclusive Language Writing in Italian Formal Communications
ACM Transactions on Intelligent Systems and Technology (2025) 🔗 [paper] • [code]
→ AI-based writing assistance system supporting humans in adopting inclusive language in Italian formal communications. -
NLPGuard: Mitigating Protected Attribute Use in NLP Classifiers
ACM Conference on Computer-Supported Cooperative Work and Social Computing (2024) 🔗 [paper] • [code]
→ Fairness framework that reduces reliance on protected attributes without reducing predictive performance.