me-2023.jpg
Khanh X. Nguyen

kxnguyen AT berkeley.edu

I am a Postdoctoral Research Fellow of the Center for Human-Compatible Artificial Intelligence (CHAI) at the University of California–Berkeley, where I am fortunate to be mentored by Prof. Stuart Russell. Previously, I was a postdoc at the Princeton NLP group working with Prof. Karthik Narasimhan. I obtained my PhD at the University of Maryland–College Park, advised by Prof. Hal Daumé III.

My general goal is to create artificial agents that can be easily controlled by humans. I believe that is the necessary first step to make AI safe and useful enough to benefit our society. My work designs learning algorithms that support the human natural ways of communication:

  • Learning from human feedback: I worked on reinforcement learning from human feedback (RLHF) since the pre-LLM days [EMNLP’17]. Recently, I have been developing frameworks for learning via abstract, pragmatic language-based communication [ICML’21, ArXiv’23].
  • Learning to ask questions: agents that can ask questions enjoy improved interpretability, safety, and utility! I have written a series of papers to disseminate this idea [EMNLP’15’, CVPR’19, EMNLP’19, ICML’22].
  • Modeling human cognition: current models implement a very primitive “model of thought” [ToM@ICML’23]. To communicate effectively with humans, their cognition must be robust and human-compatible. I recently improved the cognitive capbility of instruction-generation models [ACL’23].

More facts:

  • My real name is Nguyễn Xuân Khánh :loud_sound:. My first name (Khanh) means “joy” or “happiness”. Please do not confuse it with Khan or Kahn :(
  • I was born in Việt Nam :vietnam:, a peaceful country (click here for inspiration to visit us).
  • I am also proud to be a PTNK (Phổ Thông Năng Khiếu) alumnus.

news

Dec 20, 2022 New paper on task-oriented cognitive capabilities. TLDR; we found and improved the deficiency in the pragmatic capability of instruction generation models. Received outstanding paper award at the ToM workshop at ICML 2023.
Aug 17, 2022 I will be organizing InterNLP workshop at NeurIPS 2022. Please submit your papers if interested!

selected publications

  1. Khanh Nguyen, Yonatan Bisk, and Hal Daumé III
    ICML, Jul 2022

    💡 Agents that can decide when and what question to ask, and incoporate answer to make progress

  2. Khanh Nguyen, Dipendra Misra, Robert Schapire, Miro Dudı́k, and Patrick Shafto
    ICML, Jul 2021

    💡 Framework for learning from language feedback with theoretical guarantees

  3. Khanh Nguyen, Hal Daumé III, and Jordan Boyd-Graber
    EMNLP, Sep 2017

    💡 Improve machine translation with reinforcement learning from noisy ratings

  4. Khanh Nguyen, and Brendan O’Connor
    EMNLP, Sep 2015

    💡 Calibrated probabilities for detecting errors of NLP models