Francesco Sovrano

Francesco is a computer scientist and data science researcher focused on explainability for responsible AI. He earned a PhD in Data Science and Computation in 2023 from the University of Bologna, in association with the Polytechnic University of Milan, developing a computational theory of explanations with applications in user interfaces, regulatory compliance, and reinforcement learning. As a Postdoctoral Researcher at the University of Zurich, he applied explanation theories to software engineering, AI in education, and EU regulation, while also researching machine learning for code. He later became an Early-Career Fellow at ETH Zurich’s Collegium Helveticum, creating explainable AI (XAI) tools to reveal rules and biases in LLM-generated explanations. He is currently a postdoctoral researcher at the University of Italian-speaking Switzerland (USI), working on an InnoSuisse project on XAI for financial crime detection in collaboration with Deloitte AG. His work aims to identify and mitigate cognitive and statistical biases in human-AI interaction, advancing transparent, ethical, and trustworthy AI.

Francesco Sovrano is a computer scientist and data science researcher specializing in explainable and responsible AI (XAI), with a particular emphasis on the philosophical, human, and algorithmic dimensions of explanation and explainable AI, and its applications in software engineering and law for knowledge discovery, debugging, and compliance. As a practicing data scientist, his work is characterized by high interdisciplinarity and at times touches upon secondary topics including: AI in education, human-computer interaction, natural language processing, and reinforcement learning.