References

• 2023ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope2,455 cited
• 2018Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science840 cited
• 2021StereoSet: Measuring stereotypical bias in pretrained language models643 cited
• 2023Gender bias and stereotypes in Large Language Models381 cited
• 2019Gender Bias in Contextualized Word Embeddings334 cited
• 2021Five sources of bias in natural language processing298 cited
• 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection286 cited
• 2023Should ChatGPT be biased? Challenges and risks of bias in large language models282 cited
• 2021Towards Understanding and Mitigating Social Biases in Language Models153 cited
• 2020Investigating Gender Bias in Language Models Using Causal Mediation Analysis142 cited
• 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models72 cited
• 2022Quantifying and alleviating political bias in language models68 cited
• 2021Mitigating Political Bias in Language Models through Reinforced Calibration64 cited
• 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models