,

I defended my doctoral dissertation, « Construction of Model Behavior by Novices through Interaction with Machine Learning », in October 2025 at Université Paris-Saclay. I was supervised by Jules Françoise, Baptiste Caramiaux, and Michèle Gouiffès. In my thesis, I approached ML models as sociotechnical artifacts whose behavior unfolds through users’ interactions with them in context. I explored this through two empirical studies with novice users. The first focused on how novices could negotiate and shape model behavior during the development phase by collaboratively teaching their domain expertise to the model; this work was published at ACM IUI 2024. The second investigated how to support novices in making sense of model behavior and evaluating it during use, once the model is deployed. This work was published at ACM CHI 2026 and received a Best Paper Award 🏆 (top 1% of submissions).
More broadly, my thesis calls for deeper engagement with the social, political, and epistemic conditions that shape ML systems,
toward a more participatory and reflexive vision of human-centered AI,
and with particular attention to user interaction! 🎈