Scholar
Rajiv Movva
Google Scholar ID: OLbbUjcAAAAJ
UC Berkeley
Citations & Impact
Citations
468
H-index
10
i10-index
10
Publications
18
Co-authors
1
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including Sparse Autoencoders for Hypothesis Generation at ICML 2025, Annotation alignment: Comparing LLM and human annotations of conversational safety at EMNLP 2024, and Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers at NAACL 2024. Received several awards, such as Best Student Paper at FAccT 2022 and Best Paper at BlackboxNLP @ EMNLP 2020.
Research Experience
- Worked on several research projects including HypotheSAEs (an approach to generate hypotheses from labeled text datasets) and What’s In My Human Feedback? (a tool for LLM researchers to understand what’s encoded in human feedback data). Worked under the guidance of Catherine D’Ignazio, Michael Carbin, and Anshul Kundaje.
Education
- PhD: University of California, Berkeley, Computer Science, advised by Emma Pierson; Previously at Cornell Tech, member of the AI, Policy, and Practice group and a Digital Life Initiative fellow; Undergraduate at MIT, major in Computer Science with minors in Biology and Women’s & Gender Studies.
Background
- Research Interests: Human-centered AI for science, particularly new methods leveraging foundation models to advance scientific research. Very excited about applications in biomedicine, social science, and the social impacts of AI.
Miscellany
- Writes sporadically on his blog and Substack.
