Making Adversarially-Trained Language Models Forget with Model Retraining: A Case Study on Hate Speech Detection.

@inproceedings{omar-2022-making, author = {Marwan Omar and David Mohaisen}, editor = {Fr\'{e}d\'{e}rique Laforest and Rapha\"{e}l Troncy and Elena Simperl and Deepak Agarwal and Aristides Gionis and Ivan Herman and Lionel M\'{e}dini}, title = {{Making Adversarially-Trained Language Models Forget with Model Retraining: A Case Study on Hate Speech Detection}}, booktitle = {{Companion of The Web Conference 2022, Virtual Event / Lyon, France, April 25 - 29, 2022}}, pages = {887--893}, publisher = {ACM}, year = {2022}, url = {https://doi.org/10.1145/3487553.3524667}, doi = {https://doi.org/10.1145/3487553.3524667} }