Tai Nguyen


May 2021: Hours before abseiling down Sơn Đoòng.

I’m Tai (Nguyễn Đặng Đức Tài), a graduate student at the University of Pennsylvania. I grew up in Saigon, Vietnam. 🇻🇳

I am excited about topics related to robustness, interpretability, and efficiency in LLMs and modern AI systems. I was fortunate to work with Eric Wong and Chris Callison-Burch.

Previously, I spent 2 memorable years as a data scientist at IBM Systems.
I helped build an analysis tool to support daily diagnosis and development of System-z mainframe servers.

Before NLP, I studied Economics and Statistics at Haverford College. I wrote my undergraduate thesis on the impact of home sharing on welfare, working with professor Giri Parameswaran.

If you’d like to chat, please reach me at taing [at] seas [dot] upenn [dot] edu.

I am looking to apply to PhD programs in the US for Fall 2024.

publications (* Equal contribution)

  1. In-context Example Selection with Influences
    Tai Nguyen, and Eric Wong
    In submission, 2023
  2. Explanation-based Finetuning Makes Models More Robust to Spurious Cues
    Josh Ludan, Yixuan Meng*, Tai Nguyen*, Saurabh Shah*, Qing Lyu, Marianna Apidianaki, and Chris Callison-Burch
    Association for Computational Linguistics, ACL 2023
  3. Software Entity Recognition with Noise-robust Learning
    Tai Nguyen, Yifeng Di, Joohan Lee, Muhao Chen, and Tianyi Zhang
    IEEE/ACM International Conference on Automated Software Engineering, ASE 2023