I am a third-year CS PhD student at UC Berkeley, advised by Emma Pierson. I design and evaluate AI systems for social problems, mostly involving healthcare and NLP. My prior work focuses on improving ML fairness audits (MLHC 2023), using LLMs for health equity (NEJM AI 2025), and measuring pluralistic alignment in language models (EMNLP 2024). Recently, I’m excited about interpreting foundation models to drive scientific discovery (arXiv 2025).
I started my PhD at Cornell Tech, and I continue to collaborate with the AI, Policy, and Practice working group. I was part of the Digital Life Initiative. In 2024, I interned with the FATE group at Microsoft Research Montréal. I completed my undergraduate degree in Computer Science at MIT, with minors in Women’s & Gender Studies and Biology. I worked with the Data + Feminism Lab and the Programming Systems Group.
I occasionally write things here. I like cooking, and I occasionally write food-related things on Substack. I am grateful to all the mentors and collaborators who have helped me along the way; if I can be helpful, I am always happy to chat via email.
Recently:
- [Nov 2024] I will transfer to the UC Berkeley Computer Science PhD program, starting in January 2025, and will continue to work with Emma Pierson there.
- [Nov 2024] New blog post: GenAI’s Burden of Authenticity. Please send any thoughts!
- [Sep 2024] Our work on LLM annotation alignment is accepted at EMNLP 2024!
- [Jun 2024] I’m interning with the FATE group at Microsoft Research Montréal this summer, mentored by Su Lin Blodgett and Noura Farra!
Selected Work
Sparse Autoencoders for Hypothesis Generation.
Rajiv Movva*, Kenny Peng*, Nikhil Garg, Jon Kleinberg, Emma Pierson.
arXiv 2025.
[working draft]
Annotation alignment: Comparing LLM and human annotations of conversational safety.
Rajiv Movva, Pang Wei Koh, Emma Pierson.
EMNLP 2024.
[paper] [twitter]
Coarse race data conceals disparities in clinical risk score performance.
Rajiv Movva*, Divya Shanmugam*, Kaihua Hou, Priya Pathak, John Guttag, Nikhil Garg, Emma Pierson.
MLHC 2023 (Proceedings) & ML4H 2023 (Findings).
🏆 Honorable Mention, Best Findings Paper 🏆, ML4H 2023.
[paper] [twitter] [code] [Cornell news] [New York Times]
Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers.
Rajiv Movva*, Sidhika Balachandar*, Kenny Peng*, Gabriel Agostini*, Nikhil Garg, Emma Pierson.
NAACL 2024.
[paper] [twitter] [code] [Data Skeptic podcast]
Towards Intersectional, Feminist, Participatory ML: A Case Study in Supporting Feminicide Counterdata Collection.
Harini Suresh, Rajiv Movva, Amelia Dogan, Rahul Bhargava, Isadora Cruxên, Ángeles Martinez Cuba, Giulia Taurino, Wonyoung So, Catherine D’Ignazio.
FAccT 2022.
🏆 Best Student Paper 🏆
[paper] [twitter]