mlsanityData to 7 Oct 2026

Evaluating Debiasing Techniques for Intersectional Biases

arXiv 2109.10441 ↗First posted 21 Sep 2021cs.CLcited by 30

Not on the map. Why?

Abstract (arXiv)

Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or race, however many corpora involve multiple such attributes, possibly with higher cardinality. In this paper we argue that a truly fair model must consider `gerrymandering' groups which comprise not only single attributes, but also intersectional groups. We evaluate a form of bias-constrained model which is new to NLP, as well an extension of the iterative nullspace projection technique which can handle multiple protected attributes.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

16 of 23 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  4. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  5. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  6. 2019On Measuring Social Biases in Sentence Encoderscited by 397
  7. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  8. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  9. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  10. 2020UnQovering Stereotyping Biases via Underspecified Questionscited by 124
  11. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  12. 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
4 more
  1. 2018Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraintscited by 53
  2. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  3. 2020Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognitioncited by 43
  4. 2017Iterative Supervised Principal Componentscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 9; 2023: 11; 2024: 7; 2025: 3.

30 papers.

Sort:

By area:

  1. 2023Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMscited by 176
  2. 2022Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotationcited by 67
  3. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  4. 2022MABEL: Attenuating Gender Bias using Textual Entailment Datacited by 31
  5. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  6. 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
  7. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  8. 2022Controlling Bias Exposure for Fair Interpretable Predictionscited by 18
  9. 2023Fairness in Language Models Beyond English: Gaps and Challengescited by 16
  10. 2022Learning Fair Representations via Rate-Distortion Maximizationcited by 15
  11. 2023Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLPcited by 11
  12. 2023iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?cited by 10
18 more
  1. 2024MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Modelscited by 10
  2. 2024Fairness Definitions in Language Models Explainedcited by 10
  3. 2022Towards Equal Opportunity Fairness through Adversarial Learningcited by 8
  4. 2025Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Managementcited by 7
  5. 2022Bridging Fairness and Environmental Sustainability in Natural Language Processingcited by 5
  6. 2023DSAP: Analyzing Bias Through Demographic Comparison of Datasetscited by 5
  7. 2024Addressing Both Statistical and Causal Gender Fairness in NLP Modelscited by 4
  8. 2022Systematic Evaluation of Predictive Fairnesscited by 3
  9. 2024Protected group bias and stereotypes in Large Language Modelscited by 3
  10. 2024Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Softwarecited by 3
  11. 2023Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasetscited by 2
  12. 2023Fair Without Leveling Down: A New Intersectional Fairness Definitioncited by 1
  13. 2024A Note on Bias to Completecited by 1
  14. 2023Transferring Fairness using Multi-Task Learning with Limited Demographic Informationcited by 0
  15. 2023Auditing Predictive Models for Intersectional Biasescited by 0
  16. 2024Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Modelscited by 0
  17. 2025A Survey on Stereotype Detection in Natural Language Processingcited by 0
  18. 2025A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontierscited by 0