Hi! I am Kundan Krishna. I am an ML researcher in the Responsible AI group at Apple. My research interests include assessing and improving safety of systems based on foundation models, synthetic data generation, and AI alignment. Previously, I completed my PhD at the Language Technologies Institute at Carnegie Mellon University advised by Professor Zachary Lipton and Professor Jeffrey Bigham. My thesis explored approaches to improve the robustness and truthfulness of language models when used for summarization.