Mario Giulianelli

I am an Associate Professor of Computational Linguistics at UCL and a member of the European Laboratory for Learning and Intelligent Systems. Prior to this, I was a senior research scientist at the UK AI Security Institute, working on the (nascent) science of AI evaluation, and a postdoctoral fellow at ETH Zurich, working with Ryan Cotterell in the Institute for Machine Learning, Department of Computer Science. I did my PhD at the Institute for Logic, Language and Computation of the University of Amsterdam, where I was advised by Raquel Fernández.

My research explores the computational principles underlying the ability to understand, produce, learn, and use language in interaction—both in human and in artificial language processing systems. I’m also increasingly interested in biological and artificial cognitive systems more broadly, and by extension to extra-linguistic aspects of perception, action, and interaction. In 2018, I co-authored a paper that, according to the very kind Aaron Mueller, introduced the first causal (mechanistic) interpretability method for language models—apparently before it was cool. I am deeply committed to advancing evaluation standards for AI systems, with a focus on language as well as broader aspects of agency and safety.

News

Working with me

Before e-mailing me, please read the following!

Invited talks and guest lectures

Work in progress

Publications

Theses