mlsanityData to 7 Oct 2026

Predicting the Type and Target of Offensive Posts in Social Media

arXiv 1902.09666 ↗First posted 25 Feb 2019cs.CLcited by 268

Not on the map. Why?

Cited by 24 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As offensive content has become pervasive in social media, there has been much research in identifying potentially offensive messages. However, previous work on this topic did not consider the problem as a whole, but rather focused on detecting very specific types of offensive content, e.g., hate speech, cyberbulling, or cyber-aggression. In contrast, here we target several different kinds of offensive content. In particular, we model the task hierarchically, identifying the type and the target of offensive messages in social media. For this purpose, we complied the Offensive Language Identification Dataset (OLID), a new dataset with tweets annotated for offensive content using a fine-grained three-layer annotation scheme, which we make publicly available. We discuss the main similarities and differences between OLID and pre-existing datasets for hate speech identification, aggression detection, and similar tasks. We further experiment with and we compare the performance of different machine learning models on OLID.

Key facts. Cited by 268 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 51; 2023: 61; 2024: 50; 2025: 29; 2026: 17.

268 papers.

Sort:

By area:

  1. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  2. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  3. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  4. 2023Large Language Model Alignment: A Surveycited by 241
  5. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  6. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 203
  7. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 124
  8. 2022Fusing finetuned models for better pretrainingcited by 110
  9. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 96
  10. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 87
  11. 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 85
  12. 2022COLD: A Benchmark for Chinese Offensive Language Detectioncited by 74
38 more
  1. 2021On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmarkcited by 73
  2. 2024Safeguarding Large Language Models: A Surveycited by 73
  3. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  4. 2021Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreementcited by 71
  5. 2023Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learningcited by 69
  6. 2023Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Modelscited by 68
  7. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  8. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 62
  9. 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labelscited by 61
  10. 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
  11. 2023Knowledge is a Region in Weight Space for Fine-tuned Language Modelscited by 58
  12. 2021Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contextscited by 56
  13. 2022ColD Fusion: Collaborative Descent for Distributed Multitask Finetuningcited by 52
  14. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  15. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learningcited by 47
  16. 2021ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AIcited by 46
  17. 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attackscited by 44
  18. 2023Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysiscited by 44
  19. 2021Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languagescited by 38
  20. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Modelscited by 36
  21. 2022Toxicity Detection with Generative Prompt-based Inferencecited by 35
  22. 2023COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statementscited by 34
  23. 2021Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Gocited by 32
  24. 2024Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Modelscited by 31
  25. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 31
  26. 2021MUDES: Multilingual Detection of Offensive Spanscited by 30
  27. 2021FBERT: A Neural Transformer for Identifying Offensive Contentcited by 30
  28. 2021Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathicited by 28
  29. 2023Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluationcited by 28
  30. 2021A systematic review of Hate Speech automatic detection using Natural Language Processingcited by 26
  31. 2022Evaluating Psychological Safety of Large Language Modelscited by 26
  32. 2023TrojText: Test-time Invisible Textual Trojan Insertioncited by 26
  33. 2023From Shortcuts to Triggers: Backdoor Defense with Denoised PoEcited by 26
  34. 2021A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Textscited by 25
  35. 2023Defending against Insertion-based Textual Backdoor Attacks via Attributioncited by 24
  36. 2022APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversationscited by 23
  37. 2022Where to start? Analyzing the potential value of intermediate modelscited by 23
  38. 2021Multilingual Offensive Language Identification for Low-resource Languagescited by 22

50 most cited of 268 All 268 (JSON)