mlsanityData to 7 Oct 2026

Mitigating Gender Bias Amplification in Distribution by Posterior Regularization

arXiv 2005.06251 ↗First posted 13 May 2020cs.CL cs.CV cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., Zhao et al. (2017) show that these techniques inadvertently capture the societal bias hidden in the corpus and further amplify it. However, their analysis is conducted only on models' top predictions. In this paper, we investigate the gender bias amplification issue from the distribution perspective and demonstrate that the bias is amplified in the view of predicted probability distribution over labels. We further propose a bias mitigation approach based on posterior regularization. With little performance loss, our method can almost remove the bias amplification in the distribution. Our study sheds the light on understanding the bias amplification.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 10; 2023: 7; 2024: 5; 2025: 1.

27 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  3. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  4. 2022A Systematic Study of Bias Amplificationcited by 65
  5. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  6. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 58
  7. 2021Directional Bias Amplificationcited by 54
  8. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  9. 2022Gender and Racial Bias in Visual Question Answering Datasetscited by 39
  10. 2022Quantifying Societal Bias Amplification in Image Captioningcited by 37
  11. 2024IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Contextcited by 32
  12. 2022Causally Testing Gender Bias in LLMs: A Case Study on Occupational Biascited by 28
15 more
  1. 2022Men Also Do Laundry: Multi-Attribute Bias Amplificationcited by 21
  2. 2021Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classificationcited by 20
  3. 2023Model-Agnostic Gender Debiased Image Captioningcited by 17
  4. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  5. 2022Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networkscited by 10
  6. 2022Trustworthy Social Bias Measurementcited by 7
  7. 2023Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustnesscited by 7
  8. 2021Learning Stable Classifiers by Transferring Unstable Featurescited by 6
  9. 2023Measuring Sentiment Bias in Machine Translationcited by 5
  10. 2024The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Modelscited by 5
  11. 2023Fair Text Classification with Wasserstein Independencecited by 4
  12. 2024Addressing Discretization-Induced Bias in Demographic Predictioncited by 4
  13. 2024Protected group bias and stereotypes in Large Language Modelscited by 3
  14. 2022A methodology to characterize bias and harmful stereotypes in natural language processing in Latin Americacited by 2
  15. 2025CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalizationcited by 1