I am a Postdoctoral Research Fellow of the Center for Human-Compatible Artificial Intelligence (CHAI) at the University of California, Berkeley. I am fortunate to be mentored by Prof. Stuart Russell. Previously, I spent a year as a postdoc at the Princeton NLP group under the supervision of Prof. Karthik Narasimhan. I completed my PhD at the University of Maryland–College Park, advised by Prof. Hal Daumé III.
My research focuses on enabling humans to better control and collaborate with AI. To achieve this goal, I devise AI agents that can communicate effectively with humans. For a long time, we have been communicating with AI agents in very primitive ways: we teach them with rewards and labels; they convey uncertainty to us through probabilities; most of the time, they perform tasks own their own without sharing information or asking us to help. LLMs offer better ways to control AI through language, but it is unclear whether key elements of human-like communication like inferentiality are present. My goal is to create new foundations for helpful and safe AI by going beyond the current primitive forms of human-AI communication. Specifically, I have been pushing forward three directions:
- Learning from natural human feedback: my paper [EMNLP’17] is one of the first to analyze the benefits and risks of using reinforcement learning from human feedback (RLHF) for text generation. Since then, I don’t think teaching agents with only numbers is a good idea. More recently, I developed a theoretically-grounded framework for learning from language feedback [ICML’21].
- Learning to express uncertainties and ask questions: It is a mistake to think that only humans should ask AI for help and not the reverse. By asking a question, an agent can: (i) express its uncertainties (not just uncertainty), and (ii) obtain information to expand its task-solving capabilities. So more safety and more utility! I author a series of papers that highlight the challenges and devise solutions for the problem of learning to convey uncertainties and ask good questions [EMNLP’15’, CVPR’19, EMNLP’19, ICML’22].
- Modeling humans and the world: I show that current large generative models like GPT-4 implement a very primitive “model of thought” [ToM@ICML’23]. To become more reliable, they need to develop robust models of the world and the humans in it, which allows them to simulate the future and plan appropriate actions. I take an inital step in this direction by improving the pragmatic-reasoning capbility of instruction-generation models [ACL’23].
- My real name is Nguyễn Xuân Khánh . My first name is usually confused with
- I was born in Việt Nam , a peaceful country (click here for inspiration to visit us).
- I am also proud to be a PTNK (Phổ Thông Năng Khiếu) alumnus.
|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!|
- Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation LearningIn EMNLP, 2019
- Interactive Learning from Activity DescriptionIn ICML, 2021
- Posterior calibration and exploratory analysis for natural language processing modelsIn EMNLP, Sep 2015
- Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human FeedbackIn EMNLP, Sep 2017
- A Framework for Learning to Request Rich and Contextually Useful Information from HumansIn ICML, Jul 2022