My name is Narutatsu, but please feel free to call me Edward or Tatsu. I am a PhD student at Princeton University in the Computer Science Department and Princeton Language + Intelligence (PLI), where I am fortunate to be advised by Professor Sanjeev Arora. I also work closely with Professor Micah Goldblum at Columbia University. I am gratefully supported by the Gordon Wu Fellowship and the Ezoe Memorial Recruit Foundation.
I previously finished my B.S./M.S. at Columbia University where I was part of the Egleston Scholars Program. I am indebted to Professors Kathleen McKeown, Daniel Hsu, and Nakul Verma, by whom I have had the great fortune of being advised.
Please find my CV here.
Google Scholar · GitHub · Twitter · Email
Dear prospective collaborators: for information.
Thank you very much for your interest in reaching out! I'm always more than happy to chat with people, and to work with potential collaborators and students.
For collaborators: Feel free to email me about any research topics or ideas you'd like to explore together. It may help to take a look at my selected publications to get a sense of the areas I can help with.
For Princeton undergraduate/master's students: If you're already at Princeton and interested in research opportunities, please email me with your CV, transcript, and a brief description of your research interests.
For non-Princeton students: My bandwidth may be limited, but I'm still more than happy to chat! That said, arranging access to campus compute and files may be difficult. If you're interested in remote collaboration and have access to the compute needed for your research interests, please reach out via email.
Do Thinking Tokens Help with Safety?
, Abhishek Panigrahi, Sanjeev Arora
ICML 2026 AI4GOOD Workshop (Oral)
Measuring the Limits of Continual Learning for LLMs
Nimit Kalra*, *, Zerzar Bukhari, Ang Li, Sanae
Lotfi, Liam Fowl, Micah Goldblum
ICML 2026 CompLearn Workshop
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur, , Yinghui He, Liam Fowl, Sanjeev
Arora
ICML 2026 FoGen Workshop
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Yinghui He, Simran Kaur, Adithya Bhaskar, Yongjin Yang, Jiarui Liu, , Liam Fowl, Abhishek Panigrahi, Danqi Chen,
Sanjeev Arora
ICML 2026 RLxF Workshop (Oral)
Reranking-based Generation for Unbiased Perspective Summarization
, Nicholas Deas, Kathleen McKeown
ACL 2025 (Findings)
Speak Easy: Eliciting Harmful Instructions from LLMs with Simple Interactions
Yik Siu Chan*, *, Yuxin Xiao*, Marzyeh Ghassemi
ICML 2025
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship
Attribution
Milad Alshomary, , Marianna Apidianaki, Ajay
Patel,
Smaranda Muresan, Kathleen McKeown
COLING 2025
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language
Explanations
Yanda Chen, Ruiqi Zhong, , Chen Zhao, He He,
Jacob Steinhardt,
Zhou Yu, Kathleen McKeown
ICML 2024 (Spotlight)
Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt
Design
Strategies
Linyong Nan, Yilun Zhao, Weijin Zou, , Jaesung
Tae, Ellen
Zhang, Arman Cohan, Dragomir Radev
EMNLP 2023 (Findings)
The Effect of Model Capacity on the Emergence of In-Context Learning in Transformers
Berkan Ottlik*, *, Daniel Hsu, Clayton Sanford
ICLR 2024 (ME-FoMo Workshop)
Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
, Fei-Tzin Lee, Nakul Verma
ACL 2023 (RepL4NLP Workshop)