About me
I’m a postdoctoral researcher at the University of Bonn, doing research on LLMs reasoning, robustness, and AI safety at Conversational AI and Social Analytics (CAISA) Lab led by Prof. Lucie Flek.
I did my PhD at the University of Parma under the supervision of Prof. Andrea Prati at IMP Lab, where I did research on making language models more robust using adversarial learning and data augmentation techniques.