Hello! My name is Nari (rhymes with “Atari”) and I am a second year PhD student in Carnegie Mellon University’s Machine Learning Department advised by Ameet Talwalkar. I graduated from Harvard in 2021 with a BA and MS in Computer Science, where I am grateful to have worked with Finale Doshi-Velez.

My research is motivated by the goal of developing models that are “right for the right reasons” to anticipate and mitigate potential algorithmic harm. I study tools (such as model explanations or interactive visualizations) designed to help humans understand model behavior.

More recently, I have been interested in methods to “fix” brittle models, i.e. correct systemic model errors such as reliance on spurious features. I am also interested in how we can incorporate human supervision into model training.

Selected Work

  • Evaluating Systemic Error Detection Methods using Synthetic Images.
    ICML Workshop on Spurious Correlations, Invariance, and Stability, 2022
    Gregory Plumb*, Nari Johnson*, Ángel Alexander Cabrera, Marco Tulio Ribeiro, Ameet Talwalkar
  • Use-Case-Grounded Simulations for Explanation Evaluation.
    NeurIPS, 2022
    Valerie Chen, Nari Johnson, Nicholay Topin*, Gregory Plumb*, Ameet Talwalkar.
  • OpenXAI: Towards a Transparent Evaluation of Model Explanations.
    NeurIPS Datasets & Benchmarks Track, 2022
    ICLR Pair2Struct Workshop, 2022 (Oral)
    Chirag Agarwal, Eshika Saxena, Satyapriya Krishna, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju.
  • Learning Predictive and Interpretable Timeseries Summaries from ICU Data.
    AMIA Annual Symposium, 2021
    Student Paper Competition Finalist
    Knowledge Discovery & Data Mining Student Innovation Award
    Nari Johnson, Sonali Parbhoo, Andrew Slavin Ross, Finale Doshi-Velez.

* denotes equal contribution.



I care deeply about expanding access to and creating supportive communities in computing. At CMU, I participate in the AI Mentorship Program and TechNights.

In a past life, I served as elected Co-President of Harvard Women in Computer Science and led our Advocacy Council, where I facilitated Harvard CS’s first inclusive teaching training. I also volunteered as a trained counselor for Indigo Peer Counseling.


(my first name).(my last name) (at) gmail.com