Hey! I am Navreet Kaur, a PhD student in the Information School at the University of Washington (UW), advised by Tanu Mitra. I am also affiliated with the Responsibility in AI Systems and Experiences (RAISE) centre.
I am broadly interested in Natural Language Processing, Responsible AI, Human-AI Interaction and AI Ethics. I develop human-centered evaluation frameworks that assess where AI works (or does not work) effectively, equitably and ethically. My research aims to (1) provide empirical evidence and technical tools to support AI governance, and (2) extend NLP applications to disadvantaged users while preventing harm.
Previously, I spent a wonderful year as a Research Associate at the Indian Institute of Science (IISc), under the inspiring guidance of Danish Pruthi. Before that, I worked on building anti-money laundering surveillances at Goldman Sachs. Even earlier, I graduated from IIT Delhi, where I was fortunate to be advised by Aaditeshwar Seth for my thesis.
Outside of work, I am into photography, art, travel, hiking, calisthenics, and exploring new cuisines.
Collaborate? I am always open to discussion and excited to exchange research perspectives. If you’d like to collaborate or just chat, feel free to reach out via email or Twitter!
Updates
- Jan, 2025: Knowledge Graph Guided Evaluation of Abstention Techniques is accepted to NAACL 2025! 🎉 Led by Kinshuk and mentored by Danish.
- Sep, 2024: Started my PhD at UW!
- Aug, 2024: Presented our work at ACL in Bangkok!
- May, 2024: Evaluating Large Language Models for Health-related Queries with Presuppositions is accepted to Findings of ACL 2024! 🎉
©️2025 Navreet Kaur