ICML 2022spotlight104 citations
Linear Adversarial Concept Erasure
Shauli Ravfogel, Michael Twiton, Yoav Goldberg, Ryan D Cotterell
Abstract
Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to
BibTeX
@InProceedings{pmlr-v162-ravfogel22a,
title = {Linear Adversarial Concept Erasure},
author = {Ravfogel, Shauli and Twiton, Michael and Goldberg, Yoav and Cotterell, Ryan D},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {18400--18421},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/ravfogel22a/ravfogel22a.pdf},
url = {https://proceedings.mlr.press/v162/ravfogel22a.html},
abstract = {Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to