Collegium Helveticum
Switzerland
fellow
Francesco Sovrano
2024-2025
Discipline(s)
Computers and intelligent systems; Educational Sciences
Theme(s)
Artificial Intelligence; Education & Science
Fellowship dates
›
Biography
Francesco Sovrano (born in 1991 in Camposampiero, IT) is a data scientist specializing in artificial intelligence (AI). His research spans explainable AI (XAI), law, natural language processing (NLP), and human-computer interaction (HCI). He focuses on the theory of explanations and its applications in AI to enhance learning and information acquisition. He is currently trying to decipher how generative AI like ChatGPT produces educational explanations about different concepts by integrating empirical methods and philosophical theories with XAI technology.
Francesco received his PhD in 2023 from the University of Bologna (IT), presenting a new computational theory of explanations influenced by ordinary language philosophy and novel explanatory AI technology. His research included case studies on European legal frameworks and education, highlighting the theory's practical utility in improving learning efficiency for both AI agents and humans.
Before joining the Collegium Helveticum, Francesco was a senior researcher at the University of Zurich in the Zurich Empirical Software Engineering Group from 2023 until 2024, where he continued to advance his research in AI and software explanations.
Research Project
Explaining the Unexplainable: Bridging the Gap Between Generative AI and Theory-Driven Explanations
This project aims to uncover how generative artificial intelligence (GenAI), such as ChatGPT, produces explanations in educational settings. Using grounded theory, the project will systematically analyze GenAI's explanation processes within an educational context, across disciplines including programming, law, and history. The goal is to develop an empirical-derived computational theory of explanations that will inform the creation of next-generation transparent explanatory AI systems. This endeavor aims to make AI a trustworthy educational tool, aligning with UNESCO's vision for AI in education. Despite GenAI technology's effectiveness in producing explanations, the underlying rationale remains largely unknown. Opening this "black-box" is an ongoing challenge, and current tools are insufficient. Existing explainable AI (XAI) algorithms generally fail to explain large natural language generation models effectively. This project will explore GenAI's explanation generation for historical, legal, and technological concepts by integrating empirical methods and philosophical theories with existing XAI technology.
Research Interests:
Artificial Intelligence; explainable AI; XAI, law, natural language processing; NLP; human-computer interaction; HCI; education