I am a PhD student at the MIT Operations Research Center (ORC), where I am fortunate to be advised by Professor Georgia Perakis and Professor Chara Podimata. I previously graduated from the Master of Business Analytics program at MIT ('25) and hold a Bachelor's in Economics and Computer Science from Bocconi University ('24). Outside of research, you'll usually find me playing football (soccer, for my American friends) or training outdoors.
Research interests
I work on the reliability of language models, especially when the context they are given is partial or noisy. Two settings interest me most: silicon sampling, where LLMs stand in for human subjects, and multi-turn conversations, where models drift as the dialogue grows longer. I also care about whether models stay consistent, both with themselves and with us, and about calibration. I've worked on a range of applications, including auditing AI systems and healthcare.
Publications
-
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale.
Authors: A. Morosini*, S. H. Cen*, A. Ilyas, H. Driss, A. Madry, C. Podimata. ACM Conference on Economics and Computation (EC), 2026. -
Too Sharp, Too Sure: When Calibration Follows Curvature.
Authors: A. Morosini, M. Gjika, T. Poggio, P. Beneventano. Workshop on High-dimensional Learning (HiLD) at ICML, 2026. -
ModuLearn: An Interpretable Transcriptomic Framework for Cancer
Outcome Prediction.
Authors: M. Gjika, A. Morosini, M. Panagopoulou, A. Mertzios, K. Chatzaki, G. Perakis. Preprint, 2025.