Research
Full list available on Google Scholar. Asterisks* denote co-first authorship.
Position: Use Sparse Autoencoders to Discover Unknown Concepts
Kenny Peng*, Rajiv Movva*, Jon Kleinberg, Emma Pierson, Nikhil Garg.
ICML 2026.
paper · twitter
What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
Rajiv Movva, Smitha Milli, Sewon Min, Emma Pierson.
ICLR 2026. Oral presentation.
paper · demo · code
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
Generative AI in Medicine
Divya Shanmugam, Monica Agrawal, Rajiv Movva, Irene Y. Chen, Marzyeh Ghassemi, Maia Jacobs, Emma Pierson.
Annual Review of Biomedical Data Science, 2025.
paper · twitter
Use large language models to promote equity
Emma Pierson*, Divya Shanmugam*, Rajiv Movva*, Jon Kleinberg* et al.
New England Journal of Medicine AI, 2025.
paper · preprint · twitter
Annotation alignment: Comparing LLM and human annotations of conversational safety
Rajiv Movva, Pang Wei Koh, Emma Pierson.
EMNLP 2024.
paper · twitter
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
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) and ML4H 2023 (Findings). Honorable Mention, Best Findings Paper.
paper · twitter · code · Cornell news · New York Times
Towards Intersectional, Feminist, Participatory ML: A Case Study in Supporting Feminicide Counterdata Collection
Harini Suresh, Rajiv Movva, Amelia Dogan, Rahul Bhargava, Isadora Cruxen, Angeles Martinez Cuba, Giulia Taurino, Wonyoung So, Catherine D'Ignazio.
FAccT 2022. Best Student Paper.
paper · twitter
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks
Rajiv Movva*, Jinhao Lei*, Shayne Longpre, Ajay Gupta, Chris DuBois.
COLING 2022.
paper · twitter
Studying the Consistency and Composability of Lottery Ticket Pruning Masks
Rajiv Movva, Jonathan Frankle, Michael Carbin.
ICLR Workshop on Science and Engineering of Deep Learning 2021.
paper · twitter