Verna Dankers

I am a postdoc at Mila (Quebec AI Institute) and McGill University, with Prof Siva Reddy. I completed my PhD at the University of Edinburgh’s NLP CDT, supervised by Prof Ivan Titov, and held research internships at Meta AI Research (2022) and Microsoft Research (2024).

My research focuses on understanding the memorization vs. generalization balance in LLMs — studied through behavioral analyses and interpretability techniques. I am also interested in compositionality, figurative language, multilinguality, and tokenization.