Scholar
Shauli Ravfogel
Google Scholar ID: x09r-T8AAAAJ
Faculty Fellow, NYU
Citations & Impact
Citations
4,449
H-index
23
i10-index
28
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- IAAI Best PhD Thesis Award (September 2024), Blavatnik Prize for Outstanding Israeli Doctoral Students in Computer Science (June 2024), Bloomberg Data Science PhD Fellowship (December 2022), Best Paper Award at RepL4NLP@ACL22 (May 2022). Invited talks at J.P Morgan and DeepMind. Academic visits to Bar-Ilan University, ETH Zurich, Johns Hopkins University, and others.
Research Experience
- Worked at the Natural Language Processing Lab at Bar-Ilan University, focusing on techniques to selectively control information in neural representations. More recently, he has explored framing LMs as causal models and tackling questions of learnability in a controlled setting. Teaching a new course on causality and interpretability of LMs in Spring 2025; Visited ETH Zurich from September to December 2024.
Education
- MSc in Computer Science from Bar Ilan University, BSc in Computer Science from Bar Ilan University, BSc in Chemistry from Bar Ilan University, supervised by Prof. Yoav Goldberg for his PhD.
Background
- His research interests include NLP, representation learning, and interpretability. He is a Faculty Fellow at the NYU Center of Data Science. His research focuses on analyzing and controlling the internal representations of generative models, particularly language models, studying how neural networks encode structured information, use it to solve tasks, and represent interpretable concepts.
Miscellany
- No personal interests or other information mentioned on the webpage.
