Zorik Gekhman
I am a computer science PhD student at the Technion, working with Roi Reichart, and I also work as research intern at Google Research since February 2023, where I work with Jonathan Herzig and Roee Aharoni.
I work on the robustness and interpretability of large language models, particularly in relation to factuality, hallucinations, and the nature of their learned knowledge. My research develops rigorous methods to evaluate robustness, explores the underlying causes of robustness issues, and proposes strategies to mitigate them.
Past
I worked as a full time research engineer at Google Health Research for four years, focusing on medical translation and transcription solutions.
I worked as a full time backend engineer at Microsoft Cyber Defense for three years, building a high scale cloud infrastructure in production.
I hold a BSc. in computer science from the Technion (Summa Cum Laude).