Ruiqi Zhong (

I am currently a second year PhD student in the Berekely NLP group, advised by Prof. Dan Klein and Prof. Jacob Steinhardt. I am broadly interested in the intersection of NLP with programming languages and machine learning. Specifically, I work on

  • Text-to-progrm generation: how do we map human languages to executable programs, in an interactive and multi-modal (e.g programming by examples) way.

  • Deep learning training and generalization: can we explain and predict what and how neural networks learn?
  • Stylistically, I prefer projects that unlock new lines of researches, or rethink the current conceptual framework.

    I finished my undergrad at Columbia University and was advised by Prof. Kathleen McKeown.

    Twitter Google Scholar GitHub


    Ph.D. students from the Berkeley NLP group have compiled a list of resources to prepare Berkeley undergrads for NLP researches. I am also happy to talk about research personally. Just send me an email if you wanna chat with me.

    If you specifically want to work with me, try finishing the project 2 of CS288 before contacting me.


    Meta-tuning Language Models to Answer Prompts Better
    Ruiqi Zhong, Kristy Lee, Zheng Zhang, Dan Klein
    arXiv, 2021

    Approximating How Single Head Attention Learns
    Charlie Snell, Ruiqi Zhong, Jacob Steinhardt, Dan Klein
    arXiv, 2021
    [paper] [slides] [code] [blog]

    Semantic Evaluation for Text-to-SQL with Distilled Test Suites
    Ruiqi Zhong, Tao Yu, Dan Klein
    EMNLP 2020
    [paper] [code] [slides]

    Semantic Scaffolds for Pseudocode-to-Code Generation
    Ruiqi Zhong, Mitchell Stern, Dan Klein
    ACL 2020
    [paper] [code] [video] [slides]

    Detecting and Reducing Bias in a High Stakes Domain
    Ruiqi Zhong, Yanda Chen, Desmond Patton, Charlotte Selous, Kathleen McKeown
    EMNLP 2019
    [paper] [code] [poster]

    Fine-grained Sentiment Analysis with Faithful Attention
    Ruiqi Zhong, Steven Shao, Kathleen McKeown
    arXiv preprint

    Subspace Embedding and Linear Regression with Orlicz Norm
    Alexandr Andoni, Chengyu Lin, Ying Sheng, Peilin Zhong, Ruiqi Zhong
    ICML 2018
    [paper] [video] [slides]

    Detecting Gang-Involved Escalation on Social Media using Context
    Serina Chang, Ruiqi Zhong, Ethan Adams, Fei-Tzin Lee, Siddharth Varia, Desmond Patton, William Frey, Chris Kedzie, Kathleen McKeown
    EMNLP 2018
    [paper] [code] [video]

    Paper Reading Guides (Chinese)

    Debiasing NLP: Man is to Computer Programmer as Woman is to Homemaker?
    Ruiqi Zhong, Yanda Chen, Junyao Shi

    ICML2018 Fairness ML Best Papers.
    Ruiqi Zhong, Xinyi Han


    I represented Columbia University in ACM-ICPC and Putnam Math Competition during my Sophormore year (though it seems I was the bottle-neck of our teams).
    I sleep at 11 p.m. and do not respond to later messages. Sometimes, however, I am actually awake; but I pretend not to see them anyways.
    My favorite animation character and role model is Wenli Yang in Legend of Galactical Heroes.