Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model

Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model Abhijith Chintam author Rahel Beloch author Willem Zuidema author Michael Hanna author Oskar van der Wal author 2023-12 text Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP Yonatan Belinkov editor Sophie Hao editor Jaap Jumelet editor Najoung Kim editor Arya McCarthy editor Hosein Mohebbi editor Association for Computational Linguistics Singapore conference publication chintam-etal-2023-identifying 10.18653/v1/2023.blackboxnlp-1.29 https://aclanthology.org/2023.blackboxnlp-1.29/ 2023-12 379 394