References

• 2002A model of (often mixed) stereotype content: Competence and warmth respectively follow from perceived status and competition.7,356 cited
• 2017Semantics derived automatically from language corpora contain human-like biases2,845 cited
• 2007Agency and communion from the perspective of self versus others.1,298 cited
• 2009Stereotype content model across cultures: Towards universal similarities and some differences1,076 cited
• 2020Language (Technology) is Power: A Critical Survey of “Bias” in NLP1,044 cited
• 2021StereoSet: Measuring stereotypical bias in pretrained language models643 cited
• 2019On Measuring Social Biases in Sentence Encoders461 cited
• 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models438 cited
• 2016The ABC of stereotypes about groups: Agency/socioeconomic success, conservative–progressive beliefs, and communion.309 cited
• 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection286 cited
• 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings262 cited
• 2021BOLD242 cited
• 2013Morality and behavioural regulation in groups: A social identity approach207 cited
• 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them