My research interests revolve around augmenting human decision-making with AI. This involves evaluating the interaction of the desired outcome with its context. Current practices in data-driven decisioning adopt models that span from regression to neural networks and ensemble trees which, although powerful and mostly informative, only capture correlations in the data. Correlation is hardly enough when trying to understand the effect of actions. What decision-makers need is causality.
My PhD thesis, supervised by Prof. Francesca Toni and titled “Causal Discovery for Trustworthy Artificial Intelligence” worked towards creating transparent techniques for causal discovery and its use in machine learning predictions, leveraging argumentation. Causal discovery is about drawing a graph of the relationships influencing an observed phenomenon. Argumentation is a form of non-monotonic reasoning useful for resolving conflicts in a debate. We created systems that allow humans and machines to debate about causality. This highlights cause-effect relationships, giving decision-makers the levers to drive the outcomes they seek.
Building on this, I am currently working on the CArLA Proof-of-Concept grant. My focus is on (i) improving efficiency in argumentation-based reasoning (e.g., via graph neural networks at AAAI-26 and work on gradual semantics at KR 2025) and (ii) integrating Argumentative Causal Discovery with external knowledge to improve scalability (see the under-review preprint). My broader vision is to use Causal ABA as a backbone for interactive causal discovery in high-stakes domains such as finance, healthcare, and policy.
Zihao Li, Fabrizio Russo, "Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach." CoRR, 2026.
Under review
Preesha Gehlot, Anna Rapberger, Fabrizio Russo, Francesca Toni, "Heterogeneous Graph Neural Networks for Assumption-Based Argumentation." In Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence, AAAI-26, 2026.
Fabrizio Russo, Francesca Toni, "Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework." In Proceedings of the 5th Conference on Causal Learning and Reasoning, CLeaR 2024, Lousanne, Switzerland. May 7-9, 2025 (Forthcoming), 2025.
Anna Rapberger, Fabrizio Russo, Antonio Rago, Francesca Toni, "On Gradual Semantics for Assumption-Based Argumentation." In Proceedings of the 22nd International Conference on Principles of Knowledge Representation and Reasoning, KR 2025, 2025.
Lars Bengel, Lydia Blümel, Elfia Bezou-Vrakatseli, Federico Castagna, Giulia D'Agostino, Isabelle Kuhlmann, Jack Mumford, Daphne Odekerken, Fabrizio Russo, Stefan Sarkadi, Madeleine Waller, Andreas Xydis, "Online Handbook of Argumentation for AI: Volume 4." CoRR, 2024.
Francesco Leofante, Hamed Ayoobi, Adam Dejl, Gabriel Freedman, Deniz Gorur, Junqi Jiang, Guilherme Paulino-Passos, Antonio Rago, Anna Rapberger, Fabrizio Russo, Xiang Yin, Dekai Zhang, Francesca Toni, "Contestable AI Needs Computational Argumentation." In Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning, KR 2024, Hanoi, Vietnam. November 2-8, 2024, 2024.
Fabrizio Russo, Anna Rapberger, Francesca Toni, "Argumentative Causal Discovery." CoRR, 2024.
Fabrizio Russo, Anna Rapberger, Francesca Toni, "Argumentative Causal Discovery." In Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning, KR 2024, Hanoi, Vietnam. November 2-8, 2024, 2024.
Fabrizio Russo, Francesca Toni, "Shapley-PC: Constraint-based Causal Structure Learning with Shapley Values." CoRR, 2023.
Antonio Rago, Fabrizio Russo, Emanuele Albini, Francesca Toni, Pietro Baroni, "Explaining Classifiers' Outputs with Causal Models and Argumentation." FLAP, 2023.
Fabrizio Russo, Francesca Toni, "Causal Discovery and Knowledge Injection for Contestable Neural Networks." In ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Krak'ow, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), 2023.
Fabrizio Russo, "Argumentation for Interactive Causal Discovery." In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China, 2023.
Fabrizio Russo, Francesca Toni, "Causal Discovery and Injection for Feed-Forward Neural Networks." CoRR, 2022.
Antonio Rago, Fabrizio Russo, Emanuele Albini, Pietro Baroni, Francesca Toni, "Forging Argumentative Explanations from Causal Models." In Proceedings of the 5th Workshop on Advances in Argumentation in Artificial Intelligence 2021 co-located with the 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021), Milan, Italy, November 29th, 2021, 2021.