mlsanityData to 7 Oct 2026

The State of Profanity Obfuscation in Natural Language Processing

arXiv 2210.07595 ↗First posted 14 Oct 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Work on hate speech has made the consideration of rude and harmful examples in scientific publications inevitable. This raises various problems, such as whether or not to obscure profanities. While science must accurately disclose what it does, the unwarranted spread of hate speech is harmful to readers, and increases its internet frequency. While maintaining publications' professional appearance, obfuscating profanities makes it challenging to evaluate the content, especially for non-native speakers. Surveying 150 ACL papers, we discovered that obfuscation is usually employed for English but not other languages, and even so quite uneven. We discuss the problems with obfuscation and suggest a multilingual community resource called PrOf that has a Python module to standardize profanity obfuscation processes. We believe PrOf can help scientific publication policies to make hate speech work accessible and comparable, irrespective of language.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 89 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

33 of 89 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detectioncited by 217
  3. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  4. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 215
  5. 2020HateBERT: Retraining BERT for Abusive Language Detection in Englishcited by 206
  6. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  7. 2020SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)cited by 138
  8. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 106
  9. 2019Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systemscited by 99
  10. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
  11. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
  12. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 79
21 more
  1. 2021Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreementcited by 71
  2. 2021Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contextscited by 56
  3. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  4. 2021ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AIcited by 46
  5. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  6. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  7. 2021Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resourcescited by 30
  8. 2018Challenges in Discriminating Profanity from Hate Speechcited by 23
  9. 2021How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?cited by 19
  10. 2021The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identitycited by 16
  11. 2021An Exploratory Analysis of the Relation Between Offensive Language and Mental Healthcited by 14
  12. 2021Lifelong Learning of Hate Speech Classification on Social Mediacited by 14
  13. 2021Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Datasetcited by 13
  14. 2018Neural Character-based Composition Models for Abuse Detectioncited by 11
  15. 2021Predicting Anti-Asian Hateful Users on Twitter during COVID-19cited by 11
  16. 2021Improving Counterfactual Generation for Fair Hate Speech Detectioncited by 10
  17. 2021From Toxicity in Online Comments to Incivility in American News: Proceed with Cautioncited by 8
  18. 2021Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hatecited by 8
  19. 2021Mitigating Biases in Toxic Language Detection through Invariant Rationalizationcited by 7
  20. 2021Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainabilitycited by 4
  21. 2021Modeling Profanity and Hate Speech in Social Media with Semantic Subspacescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2023Recovering from Privacy-Preserving Masking with Large Language Modelscited by 9
  2. 2022Measuring Harmful Representations in Scandinavian Language Modelscited by 7
  3. 2025Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineeringcited by 1
  4. 2026Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysiscited by 0