Publications

2022

• Does Self-Rationalization Improve Robustness to Spurious Correlations?
  Alexis Ross, Matthew E. Peters, Ana Marasovic
  EMNLP, 2022
• Tailor: Generating and Perturbing Text with Semantic Controls
  Alexis Ross*, Tongshuang Wu*, Hao Peng, Matthew E. Peters, Matt Gardner
  ACL, 2022
  [BibTex] [Code] [Video] [Generator]

2021

• Learning Models for Actionable Recourse
  Alexis Ross, Himabindu Lakkaraju, Osbert Bastani
  NeurIPS, 2021
• Competency Problems: On Finding and Removing Artifacts in Language Data
  Matt Gardner*, William Merrill*, Jesse Dodge, Matthew E. Peters, Alexis Ross, Sameer Singh, Noah Smith
  EMNLP, 2021
  [BibTex]
• Explaining NLP Models via Minimal Contrastive Editing (MiCE)
  Alexis Ross, Ana Marasovic, Matthew E. Peters
  Findings of ACL, 2021
  [BibTex] [Code] [Video]

2019

• How well do NLI models capture verb veridicality?
  Alexis Ross and Ellie Pavlick
  EMNLP, 2019
  Oral Presentation
  [BibTex] [Dataset] [Supplement] [Slides]
• Probing what different NLP tasks teach machines about function word comprehension
  Najoung Kim, Roma Patel, Adam Poliak, Alex Wang, Patrick Xia, Tom McCoy, Ian Tenney, Alexis Ross, Tal Linzen, Benjamin Van Durme, Sam Bowman, Ellie Pavlick
  *SEM, 2019
  Best Paper Award
  [BibTex]

Other Projects

• Using Linear Approximations to Explain Complex, Blackbox Classifiers
  Advised by Hima Lakkaraju and Bernhard Nickel.
  Senior Thesis, Computer Science and Philosophy, 2020.
  Hoopes Prize