The New England Mechanistic Interpretability Workshop is happening at BU on August 14. Hope to see you there!
Hi, I’m Themis(toklis) Nikas.
I’m a CS PhD student at Boston University, where I work with Professor Aaron Mueller. My research focuses on mechanistic interpretability of large language models (LLMs). I’m interested in how LLMs represent uncertainty and how that connects to confidence and calibration.
Before Boston University, I earned an integrated Master’s degree in Computer Science and Engineering from the University of Ioannina, where I worked with Professor Panayiotis Tsaparas on link analysis algorithms.
News
Presented our work "Minimizing the Cost of PageRank Fairness" at Web & Graph (WSDM workshop).