mlsanityData to 7 Oct 2026

Measuring Bias in Contextualized Word Representations

arXiv 1906.07337 ↗First posted 18 Jun 2019cs.CLcited by 275

Not on the map. Why?

Abstract (arXiv)

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case study focuses on gender bias, the proposed technique is generalizable to unveiling other biases, including in multiclass settings, such as racial and religious biases.

Key facts. Cited by 275 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 53; 2023: 71; 2024: 62; 2025: 32; 2026: 11.

275 papers.

Sort:

By area:

  1. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  2. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  3. 2021Ethical and social risks of harm from Language Modelscited by 957
  4. 2023StarCoder: may the source be with you!cited by 790
  5. 2022Galactica: A Large Language Model for Sciencecited by 736
  6. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  8. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  9. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  10. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  11. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  12. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
38 more
  1. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  2. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  3. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  4. 2022Training Data Influence Analysis and Estimation: A Surveycited by 134
  5. 2021Causal Attention for Vision-Language Taskscited by 111
  6. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  7. 2021NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Mediacited by 106
  8. 2021Sustainable Modular Debiasing of Language Modelscited by 98
  9. 2021An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Modelscited by 96
  10. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  11. 2023A Survey on Fairness in Large Language Modelscited by 91
  12. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  13. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  14. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  15. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  16. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  17. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  18. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 74
  19. 2021Low-Complexity Probing via Finding Subnetworkscited by 63
  20. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  21. 2021Post-processing for Individual Fairnesscited by 61
  22. 2021Unmasking the Mask -- Evaluating Social Biases in Masked Language Modelscited by 60
  23. 2022Gender Bias in Masked Language Models for Multiple Languagescited by 60
  24. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 59
  25. 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
  26. 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspectivecited by 57
  27. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  28. 2023TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Modelscited by 56
  29. 2021How to Adapt Your Pretrained Multilingual Model to 1600 Languagescited by 54
  30. 2021Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Modelscited by 52
  31. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  32. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 51
  33. 2023Nationality Bias in Text Generationcited by 50
  34. 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
  35. 2022BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generationcited by 48
  36. 2022Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gendercited by 47
  37. 2021Biomedical Question Answering: A Survey of Approaches and Challengescited by 46
  38. 2023MISGENDERED: Limits of Large Language Models in Understanding Pronounscited by 43

50 most cited of 275 All 275 (JSON)