References

• 2021StereoSet: Measuring stereotypical bias in pretrained language models773 cited
• 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models505 cited
• 2019On Measuring Social Biases in Sentence Encoders502 cited
• 2020Social Bias Frames: Reasoning about Social and Power Implications of Language462 cited
• 2019The Woman Worked as a Babysitter: On Biases in Language Generation445 cited
• 2019Measuring Bias in Contextualized Word Representations372 cited
• 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection286 cited
• 2021BOLD242 cited
• 2022BBQ: A hand-built bias benchmark for question answering184 cited
• 2021Towards Understanding and Mitigating Social Biases in Language Models153 cited
• 2020Investigating Gender Bias in Language Models Using Causal Mediation Analysis142 cited
• 2022An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models116 cited
• 2021HONEST: Measuring Hurtful Sentence Completion in Language Models94 cited
• 2020UNQOVERing Stereotyping Biases via Underspecified Questions62 cited
• 2022Perturbation Augmentation for Fairer NLP