Narutatsu Ri

My name is Edward, and I'm a fifth-year Master's student at Columbia University. I've had the great fortune to be advised by Prof. Kathleen McKeown, Daniel Hsu, and Nakul Verma.
I'm supported by the Egleston Scholars Program and the Ezoe Memorial Recruit Foundation.

Some Papers
* indicates co-first authorship (name reordered).

A Probabilistic Model for Analogy Parallelism in High-Dimensional Word Representations
Narutatsu Ri, Nakul Verma
arXiv 2024 (Coming Soon!)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Narutatsu Ri*, Yik Siu Chan*, Yuxin Xiao*, Marzyeh Ghassemi
arXiv 2024 (Coming Soon!)

Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
Milad Alshomary, Narutatsu Ri, Marianna Apidianaki, Ajay Patel, Smaranda Muresan, Kathleen McKeown
arXiv 2024 (Submitted to conference)

The Effect of Model Capacity on the Emergence of In-Context Learning
Narutatsu Ri*, Berkan Ottlik*, Daniel Hsu, Clayton Sanford
ICLR 2024 (ME-FoMo Workshop)

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen McKeown
ICML 2024 (Spotlight)

Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
Narutatsu Ri, Fei-Tzin Lee, Nakul Verma
ACL 2023 (RepL4NLP Workshop)

Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies
Linyong Nan, Yilun Zhao, Weijin Zou, Narutatsu Ri, Jaesung Tae, Ellen Zhang, Arman Cohan, Dragomir Radev
EMNLP 2023 (Findings)

TA Experience

Miscellaneous

[05/15/2023] Survey report on \(k\)-means++
[04/13/2023] Quick writeup on Neural Tangent Kernels
[04/05/2023] Quick writeup on experiments with Decoder-based Transformers and Model Selection
[12/19/2022] Writeup on embeddability of word analogies on the \(n\)-sphere
[07/05/2022] Presentation on Reconstructing the Cascade of Language Processing in the Brain using the Internal Computations of a Transformer-based Language Model at IRCN (University of Tokyo)
[06/13/2022] Quick report on Deep Embedded Clustering
[03/17/2021] Quick writeup on Positive & Unlabeled (PU) Learning
[06/04/2019] Paper on 文章中の潜在要素を考慮した対話システム
[04/30/2018] Some robots I've built in the past

Website design taken from Jon Barron.