I am a third-year CS PhD student at UC Berkeley, advised by Emma Pierson.
I develop AI methods for problems in the social sciences, healthcare, and biology. Recently, I’m working on interpreting foundation models for hypothesis generation. I’m also interested in evaluating the social impacts of AI.
I started my PhD at Cornell Tech, where I was a member of the AI, Policy, and Practice group and a Digital Life Initiative fellow. Before my PhD, I studied CS at MIT, with minors in Biology and Women’s & Gender Studies. I worked with Catherine D’Ignazio, Michael Carbin, and Anshul Kundaje.
I write sporadically on my blog and on Substack. I am grateful to all the mentors and collaborators who have helped me along the way. If I can be helpful, feel free to email me: rmovva@berkeley.edu.
Recently:
- 🔗 We released a Python package for HypotheSAEs. HypotheSAEs is a method to generate interpretable hypotheses from large text datasets using text embeddings, sparse autoencoders, and LLMs. It’s fast, cheap, and produces strong results on the several datasets we’ve tested it on (e.g., news headlines, Yelp reviews, Congressional speeches).
Selected Work
Sparse Autoencoders for Hypothesis Generation.
Rajiv Movva*, Kenny Peng*, Nikhil Garg, Jon Kleinberg, Emma Pierson.
ICML 2025.
[paper] [demo] [code] [pip install] [twitter]
Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts.
Kenny Peng, Rajiv Movva, Jon Kleinberg, Emma Pierson, Nikhil Garg.
Draft.
[paper] [twitter]
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]
Dissecting Lottery Ticket Transformers: Structural and Behavorial Study of Sparse Neural Machine Translation.
Rajiv Movva and Jason Zhao.
BlackboxNLP @ EMNLP 2020.
🏆 Best Paper 🏆
[paper] [twitter] [slides]
Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays.
Rajiv Movva, Peyton Greenside, Georgi K Marinov, Surag Nair, Avanti Shrikumar, Anshul Kundaje.
PLoS ONE, 2019.
[paper] [twitter]