Probing Toxic Content in Large Pre-Trained Language Models

Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit-Yan Yeung

Abstract

Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit-Yan Yeung. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
BibTeX
@inproceedings{ousidhoum2021probing,
  author = {Nedjma Ousidhoum and Xinran Zhao and Tianqing Fang and Yangqiu Song and Dit-Yan Yeung},
  title = {{Probing Toxic Content in Large Pre-Trained Language Models}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.329},
}
Figure