Research Highlights
(See Google Scholar a full list of papers)




Causal abstraction for faithful model interpretation
Atticus Geiger, Christopher Potts, Thomas Icard
pdf bibtex

Finding alignments between interpretable causal variables and distributed neural representations
Atticus Geiger*, Zhengxuan Wu*, Christopher Potts, Thomas Icard, Noah D. Goodman
CLeaR 2024
pdf bibtex

CEBaB: Estimating the causal effects of real-world concepts on NLP model behavior
Eldar D Abraham, Karel D'Oosterlinck, Amir Feder, Yair Gat, Atticus Geiger, Christopher Potts, Roi Reichart, Zhengxuan Wu
NeurIPS 2022
pdf bibtex

Inducing Causal Structure for Interpretable Neural Network
Atticus Geiger*, Zhengxuan Wu*, Hanson Lu*, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah D. Goodman, Christopher Potts
ICML 2022
pdf bibtex

Causal Abstractions of Neural Networks
Atticus Geiger*, Hanson Lu*, Thomas Icard, Christopher Potts
NeurIPS 2021
pdf bibtex

Neural natural language inference models partially embed theories of lexical entailment and negation
Atticus Geiger, Kyle Richardson, Christopher Potts
BlackBoxNLP 2020
pdf bibtex

Posing fair generalization tasks for natural language inference
Atticus Geiger, Ignacio Cases, Lauri Karttunen, Chris Potts
EMNLP 2019
pdf bibtex