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 currently a Research Scientist at Fondazione Bruno Kessler (FBK). My research interests relate to responsible and human-centric AI topics, focusing on counterfactual explanations, algorithmic recourse, causality and user-aware decision-making systems.

I am interested in studying human-centric machine learning systems, ensuring they can provably support human expertise (NeurIPS'24) while preserving human agency, especially by providing fail-safes (FAccT'25, RecSys'25) when things do not go as planned.

I hold a PhD from the University of Trento (cum laude), advised by Bruno Lepri, Andrea Passerini and Manuel Gomez-Rodriguez. I was also part of the European Laboratory for Learning and Intelligent Systems (ELLIS) PhD network. Throughout my academic journey, I conducted research as a visiting scientist or intern at several institutions, including the European Commission, Max Planck Institute for Software Systems, 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

Selected 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. Who Pays for Fairness? Rethinking Recourse under Social Burden
    Ainhize Barrainkua, Giovanni De Toni, Jose Antonio Lozano, Novi Quadrianto
    Preprint
    [paper][code]

  3. 🏆 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]

  4. 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]

  5. Towards Human-AI Complementarity with Predictions Sets
    Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri, Manuel Gomez-Rodriguez
    NeurIPS (2024)
    [paper][code]

  6. 🏆 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 (will be available soon)]

  7. 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]

  8. Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
    Giovanni De Toni, Bruno Lepri, Andrea Passerini
    Machine Learning (2023)
    [paper][code]

Teaching