mlsanityData to 7 Oct 2026

Learning Gender-Neutral Word Embeddings

arXiv 1809.01496 ↗First posted 29 Aug 2018cs.CL cs.LG stat.MLcited by 169

Not on the map. Why?

Abstract (arXiv)

Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propose a novel training procedure for learning gender-neutral word embeddings. Our approach aims to preserve gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence. Based on the proposed method, we generate a Gender-Neutral variant of GloVe (GN-GloVe). Quantitative and qualitative experiments demonstrate that GN-GloVe successfully isolates gender information without sacrificing the functionality of the embedding model.

Key facts. Cited by 169 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 38; 2023: 31; 2024: 30; 2025: 21; 2026: 9.

169 papers.

Sort:

By area:

  1. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  2. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  3. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  4. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  5. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 197
  6. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  7. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  8. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  9. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  10. 2021Gender Bias in Machine Translationcited by 116
  11. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  12. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
38 more
  1. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 79
  2. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  3. 2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
  4. 2021On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmarkcited by 73
  5. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 63
  6. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  7. 2021Unmasking the Mask -- Evaluating Social Biases in Masked Language Modelscited by 60
  8. 2022Gender Bias in Masked Language Models for Multiple Languagescited by 60
  9. 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
  10. 2021Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarkingcited by 53
  11. 2024Evaluating Gender Bias in Large Language Models via Chain-of-Thought Promptingcited by 49
  12. 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
  13. 2024Representation Surgery: Theory and Practice of Affine Steeringcited by 47
  14. 2021NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternativescited by 46
  15. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  16. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  17. 2024Gender Bias in Large Language Models across Multiple Languagescited by 35
  18. 2021Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgettingcited by 34
  19. 2022Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Informationcited by 33
  20. 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
  21. 2023A Trip Towards Fairness: Bias and De-Biasing in Large Language Modelscited by 32
  22. 2021Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resourcescited by 30
  23. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  24. 2023On the Independence of Association Bias and Empirical Fairness in Language Modelscited by 29
  25. 2021Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translationcited by 28
  26. 2021Evaluating Gender Bias in Natural Language Inferencecited by 27
  27. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  28. 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
  29. 2024Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gapscited by 24
  30. 2023Analyzing And Editing Inner Mechanisms Of Backdoored Language Modelscited by 22
  31. 2024The Impossibility of Fair LLMscited by 22
  32. 2021Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classificationcited by 20
  33. 2022Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruningcited by 20
  34. 2022ADEPT: A DEbiasing PrompT Frameworkcited by 20
  35. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  36. 2023CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigationcited by 19
  37. 2024Fairness and Bias in Multimodal AI: A Surveycited by 19
  38. 2021COVID-19 sentiment analysis via deep learning during the rise of novel casescited by 18

50 most cited of 169 All 169 (JSON)