Giovanni De Toni
Research Scientist - Mobile and Social Computing Lab
Human-centric and Responsible AI
Fondazione Bruno Kessler (FBK)

Hi 👋! I am Giovanni and I am a Research Scientist at Fondazione Bruno Kessler (FBK). My research focuses on the algorithmic challenges involved in ensuring human oversight of AI systems and understanding their effects when deployed in social contexts.

I hold a PhD from the University of Trento (cum laude), advised by Bruno Lepri and Andrea Passerini. I was also part of the European Laboratory for Learning and Intelligent Systems (ELLIS) PhD network, through which I spent some time at the Max Planck Institute for Software Systems working with Manuel Gomez Rodriguez. Throughout my academic journey, I conducted research as a visiting scientist or intern at several institutions, including the European Commission, Google X, and CERN. Before my PhD, I was a Research Scientist at VUI, Inc., a Boston-based startup (now acquired) developing innovative conversational AI technologies. In the past, I have also contributed to several open-source scientific libraries (e.g., Shogun).

---

Latest News

• 01/2026: I've officially become a member of the ELLIS Society!
• 01/2026: "Multiclass Local Calibration With the Jensen-Shannon Distance" (with C. Barbera, L. Perini, A. Passerini and A. Pugnana) has been accepted at AISTATS 2026!
• 12/2025: I'll be serving as PC Web Chair for FAccT 2026 (ACM Conference on Fairness, Accountability, and Transparency)! We are now accepting submissions on OpenReview!
• 11/2025: "Revisiting (Un)Fairness in Recourse by Minimizing Worst-Case Social Burden" (with A. Barrainkua, J. A. Lozano, and N. Quadrianto) has been accepted at AAAI 2026 as an oral!
• 11/2025: We have released a new preprint "Multiclass Local Calibration With the Jensen-Shannon Distance" (with C. Barbera, L. Perini, A. Passerini and A. Pugnana).
• 10/2025: We have released a new preprint "To Ask or Not to Ask: Learning to Require Human Feedback" (with A. Pugnana, C. Barbera, R. Pellungrini, B. Lepri and A. Passerini).
• 09/2025: Our latest paper (with E. Purificato, E. Gomez, B. Lepri, A. Passerini and C. Consonni) received the Best Full Paper Award 🏆 at ACM RecSys 2025!
• 09/2025: We have released a new preprint "Revisiting (Un)Fairness in Recourse by Minimizing Worst-Case Social Burden" (with A. Barrainkua, J. A. Lozano, and N. Quadrianto).
• 07/2025: "You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control" (with E. Purificato, E. Gomez, B. Lepri, A. Passerini and C. Consonni) has been accepted at ACM RecSys 2025!
• 05/2025: I joined Fondazione Bruno Kessler (FBK) as a Research Scientist!
• Older News

Publications & Preprints

1. To Ask or Not to Ask: Learning to Require Human Feedback
   Andrea Pugnana*, Giovanni De Toni*, Cesare Barbera*, Roberto Pellungrini, Bruno Lepri, Andrea Passerini
   Preprint (* equal contribution)
   [paper][code]
   
   
2. Multiclass Local Calibration With the Jensen-Shannon Distance
   Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini, Andrea Pugnana
   AISTATS 2026 (to appear)
   [paper][code]
   
   
3. Revisiting (Un)Fairness in Recourse by Minimizing Worst-Case Social Burden
   Ainhize Barrainkua, Giovanni De Toni, Jose Antonio Lozano, Novi Quadrianto
   AAAI 2026 (to appear)
   Oral
   [paper][code]
   
   
4. 🏆 You Don’t Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
   Giovanni De Toni, Erasmo Purificato, Emilia Gomez, Andrea Passerini, Bruno Lepri, Cristian Consonni
   RecSys: 19th ACM Conference on Recommender Systems (2025)
   Best Full Paper Award at 19th ACM Conference on Recommender Systems (ACM RecSys 2025)
   [paper][code]
   
   
5. Time Can Invalidate Algorithmic Recourse
   Giovanni De Toni, Stefano Testo, Bruno Lepri, Andrea Passerini
   FAccT: ACM Conference on Fairness, Accountability, and Transparency (2025)
   [paper][code]
   
   
6. Towards Human-AI Complementarity with Predictions Sets
   Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri, Manuel Gomez-Rodriguez
   NeurIPS (2024)
   [paper][code]
   
   
7. 🏆 Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration
   Seyedehdelaram Esfahani, Giovanni De Toni, Bruno Lepri, Andrea Passerini, Katya Tentori, Massimo Zancanaro
   ACM UMAP (2024)
   Best Short Paper Runner-up at the 32nd ACM UMAP Conference (2024)
   [paper][code]
   
   
8. Personalized Algorithmic Recourse with Preference Elicitation
   Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri, Andrea Passerini
   Transactions on Machine Learning Research (2024)
   [paper][code]
   
   
9. Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
   Giovanni De Toni, Bruno Lepri, Andrea Passerini
   Machine Learning (2023)
   [paper][code]