mlsanityData to 7 Oct 2026

Automated Hate Speech Detection and the Problem of Offensive Language

arXiv 1703.04009 ↗First posted 11 Mar 2017cs.CLcited by 724

Not on the map. Why?

Cited by 47 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A key challenge for automatic hate-speech detection on social media is the separation of hate speech from other instances of offensive language. Lexical detection methods tend to have low precision because they classify all messages containing particular terms as hate speech and previous work using supervised learning has failed to distinguish between the two categories. We used a crowd-sourced hate speech lexicon to collect tweets containing hate speech keywords. We use crowd-sourcing to label a sample of these tweets into three categories: those containing hate speech, only offensive language, and those with neither. We train a multi-class classifier to distinguish between these different categories. Close analysis of the predictions and the errors shows when we can reliably separate hate speech from other offensive language and when this differentiation is more difficult. We find that racist and homophobic tweets are more likely to be classified as hate speech but that sexist tweets are generally classified as offensive. Tweets without explicit hate keywords are also more difficult to classify.

Key facts. Cited by 724 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 134; 2022: 118; 2023: 134; 2024: 131; 2025: 125; 2026: 82.

724 papers.

Sort:

By area:

  1. 2021MetaICL: Learning to Learn In Contextcited by 450
  2. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  3. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  4. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 328
  5. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 306
  6. 2021Understanding Dataset Difficulty with V-Usable Informationcited by 288
  7. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  8. 2023Large Language Model Alignment: A Surveycited by 241
  9. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  10. 2022A New Generation of Perspective API: Efficient Multilingual Character-level Transformerscited by 181
  11. 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 179
  12. 2021Challenges in Detoxifying Language Modelscited by 169
38 more
  1. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  2. 2022mGPT: Few-Shot Learners Go Multilingualcited by 141
  3. 2025DataSentinel: A Game-Theoretic Detection of Prompt Injection Attackscited by 124
  4. 2021On Releasing Annotator-Level Labels and Information in Datasetscited by 123
  5. 2021Entailment as Few-Shot Learnercited by 122
  6. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 112
  7. 2025Are Sparse Autoencoders Useful? A Case Study in Sparse Probingcited by 109
  8. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  9. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 96
  10. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
  11. 2021On Measures of Biases and Harms in NLPcited by 81
  12. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  13. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 79
  14. 2021Differentiable Learning Under Triagecited by 74
  15. 2022COLD: A Benchmark for Chinese Offensive Language Detectioncited by 74
  16. 2021On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmarkcited by 73
  17. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  18. 2021Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreementcited by 71
  19. 2022A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarkscited by 70
  20. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 68
  21. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 68
  22. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  23. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 62
  24. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  25. 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 59
  26. 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classificationcited by 56
  27. 2021Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contextscited by 56
  28. 2021Detecting Hate Speech with GPT-3cited by 55
  29. 2023Large Language Models to Identify Social Determinants of Health in Electronic Health Recordscited by 55
  30. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  31. 2023Unveiling the Implicit Toxicity in Large Language Modelscited by 51
  32. 2021Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hatecited by 50
  33. 2024CultureLLM: Incorporating Cultural Differences into Large Language Modelscited by 49
  34. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
  35. 2021A Survey on Multimodal Disinformation Detectioncited by 47
  36. 2021Disentangling Hate in Online Memescited by 46
  37. 2021ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AIcited by 46
  38. 2022Sample Efficient Learning of Predictors that Complement Humanscited by 46

50 most cited of 724 All 724 (JSON)