mlsanityData to 7 Oct 2026

It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations

arXiv 2005.04364 ↗First posted 9 May 2020cs.CL cs.AI cs.CYcited by 64

Not on the map. Why?

Abstract (arXiv)

Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.). We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 13; 2023: 10; 2024: 6; 2025: 7; 2026: 3.

64 papers.

Sort:

By area:

  1. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
  2. 2022Prompting GPT-3 To Be Reliablecited by 258
  3. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  4. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  5. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  6. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  7. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 74
  8. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 72
  9. 2021Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasurescited by 69
  10. 2022Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classificationcited by 52
  11. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  12. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
38 more
  1. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  2. 2022VALUE: Understanding Dialect Disparity in NLUcited by 45
  3. 2022Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Modelscited by 37
  4. 2022Data Governance in the Age of Large-Scale Data-Driven Language Technologycited by 32
  5. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 32
  6. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  7. 2021Reliability Testing for Natural Language Processing Systemscited by 25
  8. 2021Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglotscited by 23
  9. 2021Achieving Model Robustness through Discrete Adversarial Trainingcited by 23
  10. 2022Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustnesscited by 23
  11. 2021Efficient Combinatorial Optimization for Word-level Adversarial Textual Attackcited by 17
  12. 2021Token-Modification Adversarial Attacks for Natural Language Processing: A Surveycited by 12
  13. 2021On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noisecited by 9
  14. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  15. 2022Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretrainingcited by 9
  16. 2021Evaluating the Morphosyntactic Well-formedness of Generated Textscited by 8
  17. 2022Can Question Rewriting Help Conversational Question Answering?cited by 8
  18. 2023Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Textcited by 8
  19. 2022A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challengescited by 7
  20. 2021Addressing the Vulnerability of NMT in Input Perturbationscited by 6
  21. 2021Morph Call: Probing Morphosyntactic Content of Multilingual Transformerscited by 5
  22. 2021Spinning Sequence-to-Sequence Models with Meta-Backdoorscited by 5
  23. 2021Effective and Imperceptible Adversarial Textual Attack via Multi-objectivizationcited by 5
  24. 2022The Risks of Machine Learning Systemscited by 5
  25. 2023Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attackscited by 5
  26. 2021On the Universality of Deep Contextual Language Modelscited by 4
  27. 2022Are Synonym Substitution Attacks Really Synonym Substitution Attacks?cited by 4
  28. 2023Attack Named Entity Recognition by Entity Boundary Interferencecited by 4
  29. 2024Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varietiescited by 4
  30. 2024Extreme Miscalibration and the Illusion of Adversarial Robustnesscited by 4
  31. 2025Confidence Elicitation: A New Attack Vector for Large Language Modelscited by 4
  32. 2023From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Frameworkcited by 3
  33. 2024SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attackscited by 3
  34. 2025FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluationcited by 3
  35. 2021Adv-OLM: Generating Textual Adversaries via OLMcited by 2
  36. 2022Speciesist Language and Nonhuman Animal Bias in English Masked Language Modelscited by 2
  37. 2023Sample Attackability in Natural Language Adversarial Attackscited by 2
  38. 2024Algorithmic Fairness: A Tolerance Perspectivecited by 2

50 most cited of 64 All 64 (JSON)