Eric Wallace // Scholar // GitHub // Twitter

I am a first-year PhD student at UC Berkeley, where I work with Dan Klein and Dawn Song on Machine Learning and Natural Language Processing.

My current research focuses on interpreting, attacking, and understanding machine learning models. For example, understanding when and why neural models fail [1], designing new interpretation methods [2,3], and crafting adversarial attacks for NLP systems [4].

I did my undergrad at the University of Maryland, where I worked with Jordan Boyd-Graber. I spent most of 2019 working at AI2 with Matt Gardner and Sameer Singh.

  • Aug 2019: Began my PhD at UC Berkeley!
  • May 2019: Two papers accepted to ACL.
  • April 2019: Our paper Trick Me If You Can was accepted to TACL 2019.
  • April 2019: Our paper on a second-order interpretation method was accepted to ICML 2019.
  • Jan. 2019: Graduated from UMD and moved to the Allen Institute for AI (AI2).
  • Nov. 2018: Presented two works at EMNLP 2018 in Brussels, Belgium. Video here.
  • Sep. 2018: We're hosting a competition to develop Question Answering systems that can combat adversarial users
  • Aug. 2018: Paper on a new method to interpret neural NLP models accepted at EMNLP Interpretability Workshop
  • Aug. 2018: Paper on the difficulties of interpreting neural models accepted at EMNLP
  • May. 2018: Joining Lyft Self Driving as an intern this Summer in Palo Alto, CA

Positive Negative


Fantastic Student Collaborators: Shi Feng, Sewon Min, Yizhong Wang, Nikhil Kandpal, and many others
Fantastic Mentors: Dan Klein, Dawn Song, Matt Gardner, Sameer Singh, Jordan Boyd-Graber, and many others

Mohit makes great websites