mlsanityData to 7 Oct 2026

Counterfactual Multi-Token Fairness in Text Classification

arXiv 2202.03792 ↗First posted 8 Feb 2022cs.CL cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The counterfactual token generation has been limited to perturbing only a single token in texts that are generally short and single sentences. These tokens are often associated with one of many sensitive attributes. With limited counterfactuals generated, the goal to achieve invariant nature for machine learning classification models towards any sensitive attribute gets bounded, and the formulation of Counterfactual Fairness gets narrowed. In this paper, we overcome these limitations by solving root problems and opening bigger domains for understanding. We have curated a resource of sensitive tokens and their corresponding perturbation tokens, even extending the support beyond traditionally used sensitive attributes like Age, Gender, Race to Nationality, Disability, and Religion. The concept of Counterfactual Generation has been extended to multi-token support valid over all forms of texts and documents. We define the method of generating counterfactuals by perturbing multiple sensitive tokens as Counterfactual Multi-token Generation. The method has been conceptualized to showcase significant performance improvement over single-token methods and validated over multiple benchmark datasets. The emendation in counterfactual generation propagates in achieving improved Counterfactual Multi-token Fairness.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 70 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

37 of 70 references.

References · 37

  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. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018Deep contextualized word representationscited by 2,285
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  7. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  8. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  9. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 960
  10. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  11. 2017Counterfactual Fairnesscited by 802
  12. 2019On Measuring Social Biases in Sentence Encoderscited by 397
25 more
  1. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  2. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  3. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  4. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  5. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  6. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  7. 2015The Variational Fair Autoencodercited by 223
  8. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  9. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  10. 2017Avoiding Discrimination through Causal Reasoningcited by 191
  11. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  12. 2018Learning Gender-Neutral Word Embeddingscited by 169
  13. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  14. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 150
  15. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  16. 2019Perturbation Sensitivity Analysis to Detect Unintended Model Biasescited by 74
  17. 2019Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniquescited by 65
  18. 2019Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Functioncited by 57
  19. 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
  20. 2019The Sensitivity of Counterfactual Fairness to Unmeasured Confoundingcited by 35
  21. 2019Debiasing Embeddings for Reduced Gender Bias in Text Classificationcited by 19
  22. 2016Quantifying and Reducing Stereotypes in Word Embeddingscited by 14
  23. 2020Counterfactual fairness: removing direct effects through regularizationcited by 14
  24. 2020Adversarial Learning for Counterfactual Fairnesscited by 14
  25. 2019A Causal Inference Method for Reducing Gender Bias in Word Embedding Relationscited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1.

3 papers.

  1. 2022Flexible text generation for counterfactual fairness probingcited by 13
  2. 2023Counterfactually Fair Representationcited by 9
  3. 2024Addressing Both Statistical and Causal Gender Fairness in NLP Modelscited by 4