mlsanityData to 7 Oct 2026

Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings

arXiv 1904.04047 ↗First posted 3 Apr 2019cs.CL cs.LG stat.MLcited by 146

Not on the map. Why?

Abstract (arXiv)

Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 34; 2023: 26; 2024: 28; 2025: 14; 2026: 5.

146 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  3. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  4. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  5. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  6. 2021Gender Bias in Machine Translationcited by 116
  7. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  8. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 102
  9. 2021An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Modelscited by 96
  10. 2021An Interpretability Illusion for BERTcited by 94
  11. 2024Large Language Models are Geographically Biasedcited by 91
  12. 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
38 more
  1. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  2. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  3. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 79
  4. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  5. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 74
  6. 2021Low-Complexity Probing via Finding Subnetworkscited by 63
  7. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  8. 2021Unmasking the Mask -- Evaluating Social Biases in Masked Language Modelscited by 60
  9. 2022Re-contextualizing Fairness in NLP: The Case of Indiacited by 55
  10. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  11. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  12. 2022Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Informationcited by 33
  13. 2024IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Contextcited by 32
  14. 2021Evaluating Debiasing Techniques for Intersectional Biasescited by 30
  15. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  16. 2021Socially Aware Bias Measurements for Hindi Language Representationscited by 29
  17. 2022Causally Testing Gender Bias in LLMs: A Case Study on Occupational Biascited by 28
  18. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  19. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  20. 2024VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Modelcited by 26
  21. 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
  22. 2021Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Modelcited by 23
  23. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Modelscited by 23
  24. 2023NBIAS: A Natural Language Processing Framework for Bias Identification in Textcited by 23
  25. 2023Analyzing And Editing Inner Mechanisms Of Backdoored Language Modelscited by 22
  26. 2022Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairnesscited by 21
  27. 2022ADEPT: A DEbiasing PrompT Frameworkcited by 20
  28. 2023Evaluating Biased Attitude Associations of Language Models in an Intersectional Contextcited by 20
  29. 2022Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddingscited by 18
  30. 2022Fair and Argumentative Language Modeling for Computational Argumentationcited by 18
  31. 2025BiasEdit: Debiasing Stereotyped Language Models via Model Editingcited by 18
  32. 2024Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Modelscited by 15
  33. 2021Assessing the Reliability of Word Embedding Gender Bias Measurescited by 14
  34. 2022StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypescited by 14
  35. 2021On the Interaction of Belief Bias and Explanationscited by 13
  36. 2022Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabiccited by 13
  37. 2023Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Headscited by 13
  38. 2021The Arabic Parallel Gender Corpus 2.0: Extensions and Analysescited by 12

50 most cited of 146 All 146 (JSON)