About

Hi,

I’m a Postdoctoral Research Fellow at the MilaNLP group at Bocconi University. My research is generally about how language models behave as information intermediaries and how to embed democratic values in AI systems. More specifically, I investigate how political biases manifest in downstream tasks, and how they are encoded during the several training phases of LLMs and distributed in the training data. Lately, I’m also interested in evaluating LLMs for reliability, diversity, and safety in the context of information seeking.

Finally, I also enjoy thinking about the implementation of my research in real world use case applications for social good, such as news recommenders. Speaking of which, I am co-leading the project MULTIVIEW where we investigate methods for diversifying perspectives in news recommendations and how to capture multiple perspectives in news articles.

In my free time, I like to bike and free-dive. :)