Some due introductions
I am a PhD candidate in Artificial Intelligence at the University of Pisa, and I work with the Structured Machine Learning Group at the University of Trento.
My research focuses on uncertainty quantification and reliable machine learning, with particular interests in probabilistic calibration, conformal prediction, and human-AI decision making. More broadly, I am interested in developing the next generation of uncertainty-aware, trustworthy and human-centric AI frameworks.
I am always happy to chat about research, possible collaborations or interesting ideas, so feel free to reach out.
Interests
“A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge” is on arXiv
Our work on mitigating bias in LLM-as-a-judge systems is now available on arXiv.
Read abstract →“Should I Stay or Should I Show? Learning to Selectively Disclose Information” is on arXiv
Our work on learning when to selectively disclose information to decision-makers is now available on arXiv.
Read abstract →“Divide et Calibra: Multiclass Local Calibration via Vector Quantization” accepted at NeurIPS 2026
Our work on stable local calibration via discrete representations was accepted at NeurIPS 2026.
Presented “Elementary, My Dear Classifier: Interpretable Hypothesis Exclusion with Conformal Anchors” at HLDM 2026
Presented our work on interpretable, rule-based label exclusion with conformal prediction at the HLDM workshop at ECML PKDD 2026.
Presented “Multiclass Local Calibration with the Jensen–Shannon Distance”, “On the Global and Local Calibration of Graph Neural Networks”, and “Divide et Calibra: Multiclass Local Calibration via Vector Quantization” at AISTATS 2026
At AISTATS 2026 I presented and discussed three of our calibration papers during the poster sessions.
A preliminary version of “Divide et Calibra: Multiclass Local Calibration via Vector Quantization” accepted at the AISTATS 2026 calibration workshop
A preliminary version of our work on stable local calibration via discrete representations was accepted at the AISTATS 2026 workshop on trustworthy calibration.
“On the Global and Local Calibration of Graph Neural Networks” accepted at the AISTATS 2026 calibration workshop
Our work on global and local calibration in graph neural networks was accepted at the AISTATS 2026 workshop on trustworthy calibration.
“Multiclass Local Calibration with the Jensen–Shannon Distance” accepted at AISTATS 2026
Our work on consistent multiclass local calibration with LocalNets was accepted at AISTATS 2026.
“Multiclass Local Calibration with the Jensen–Shannon Distance” is on arXiv
Our work on consistent multiclass local calibration with LocalNets is now available on arXiv.
Read abstract →“Disparities in Multilingual LLM-Based Healthcare Q&A” is on arXiv
Our work on cross-lingual disparities in multilingual LLM-based healthcare Q&A is now available on arXiv.
Read abstract →“To Ask or Not to Ask: Learning to Require Human Feedback” is on arXiv
Our work on when and how to incorporate expert feedback into ML models is now available on arXiv.
Read abstract →Presented “To Ask or Not to Ask: Learning to Require Human Feedback” at HLDM 2025
Presented our work on when and how to incorporate expert feedback in machine learning models at the HLDM workshop at ECML PKDD 2025.
Presented “Interpretable and Efficient Counterfactual Generation with Disentangled Variational Autoencoders” at HLDM 2024
Presented our work on counterfactual generation and latent concept discovery via generative modelling at the HLDM workshop at ECML PKDD 2024.
Experience & Education
PhD in Artificial Intelligence
University of Pisa
Data Scientist Intern
Reale Mutua Assicurazioni
MSc in Data Science
University of Trento
BSc in Economics and Management
University of Trento