mlsanityData to 7 Oct 2026

Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting

arXiv 2110.05367 ↗First posted 11 Oct 2021cs.CL cs.CY cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated focus of the gender-neutral data, catastrophic forgetting would occur during second-phase pre-training. Forgetting information in the original training data may damage the model's downstream performance by a large margin. In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE. Then, we propose a new method, GEnder Equality Prompt (GEEP), to improve gender fairness of pre-trained models with less forgetting. GEEP freezes the pre-trained model and learns gender-related prompts with gender-neutral data. Empirical results show that GEEP not only achieves SOTA performances on gender fairness tasks, but also forgets less and performs better on GLUE by a large margin.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

26 of 37 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  8. 2018Deep contextualized word representationscited by 2,285
  9. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  10. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  11. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  12. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
14 more
  1. 2018Gender Bias in Coreference Resolutioncited by 438
  2. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  3. 2019Measuring Bias in Contextualized Word Representationscited by 275
  4. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  5. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
  6. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
  7. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  8. 2018Learning Gender-Neutral Word Embeddingscited by 169
  9. 2019Assessing Social and Intersectional Biases in Contextualized Word Representationscited by 134
  10. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  11. 2019Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Functioncited by 57
  12. 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
  13. 2021They, Them, Theirs: Rewriting with Gender-Neutral Englishcited by 44
  14. 2019WikiCREM: A Large Unsupervised Corpus for Coreference Resolutioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 5; 2024: 13; 2025: 9; 2026: 2.

34 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. 2023A Survey on Fairness in Large Language Modelscited by 91
  4. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  5. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 58
  6. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  7. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  8. 2021Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biasescited by 21
  9. 2024Fairness and Bias in Multimodal AI: A Surveycited by 19
  10. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  11. 2024From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMscited by 15
  12. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
22 more
  1. 2024Potential and Challenges of Model Editing for Social Debiasingcited by 10
  2. 2025The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generationcited by 10
  3. 2022Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Biascited by 8
  4. 2022Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructionscited by 7
  5. 2024Fairness in Large Language Models in Three Hourscited by 7
  6. 2025Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidancecited by 7
  7. 2024Improving LLM Group Fairness on Tabular Data via In-Context Learningcited by 6
  8. 2025More of the Same: Persistent Representational Harms Under Increased Representationcited by 6
  9. 2025Exposing Product Bias in LLM Investment Recommendationcited by 6
  10. 2024Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigationcited by 5
  11. 2025Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Termscited by 5
  12. 2025Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMscited by 5
  13. 2024LIDAO: Towards Limited Interventions for Debiasing (Large) Language Modelscited by 3
  14. 2024Specification Overfitting in Artificial Intelligencecited by 2
  15. 2024Expert-Guided Extinction of Toxic Tokens for Debiased Generationcited by 1
  16. 2024Collapsed Language Models Promote Fairnesscited by 1
  17. 2023Learning Horn Envelopes via Queries from Large Language Modelscited by 0
  18. 2025Mitigating Group-Level Fairness Disparities in Federated Visual Language Modelscited by 0
  19. 2025Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processingcited by 0
  20. 2025Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluationcited by 0
  21. 2026Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Modelscited by 0
  22. 2026FairNVT: Fair Classification via Noise Injection in Vision Transformerscited by 0