Alessandro Stolfo

Hi! I am a doctoral student in the Institute for Machine Learning at ETH Zürich, where I am advised by Prof. Mrinmaya Sachan, and co-advised by Prof. Yonatan Belinkov (Technion).

My research focuses on the interpretability and reliability of (large) language models. I study how models represent information and how those representations shape behavior and errors. I am excited to leverage these insights to design methods that make language models better and safer.

In summer 2024, I interned with the AI Frontiers group at Microsoft Research in Redmond, WA, where I had the opportunity to collaborate with Besmira Nushi and Eric Horvitz. Previously, in summer 2023, I interned with the Machine Learning Research Group at Oracle Labs in Burlington, MA, working with Ari Kobren.

Before starting my doctoral studies, I obtained a Master’s degree in Data Science at ETH Zürich, and I worked as a software engineer at Rethink-Resource. I completed my undergraduate studies in Computer Engineering at Politecnico di Milano.

I am grateful to be a recipient of the CYD Doctoral Fellowship.

For ETH students: Feel free to reach out via email if you’re interested in having me supervise your MSc thesis or semester project. I welcome project proposals, but even if you don’t have concrete ideas and are simply passionate about leveraging interpretability to improve models, please don’t hesitate to contact me. I typically allocate my supervision budget 4-6 weeks before the semester starts, so that’s the best timing to reach out.