mlsanityData to 7 Oct 2026

Latent Hatred: A Benchmark for Understanding Implicit Hate Speech

arXiv 2109.05322 ↗First posted 11 Sep 2021cs.CL cs.SIcited by 216

Not on the map. Why?

Abstract (arXiv)

Hate speech has grown significantly on social media, causing serious consequences for victims of all demographics. Despite much attention being paid to characterize and detect discriminatory speech, most work has focused on explicit or overt hate speech, failing to address a more pervasive form based on coded or indirect language. To fill this gap, this work introduces a theoretically-justified taxonomy of implicit hate speech and a benchmark corpus with fine-grained labels for each message and its implication. We present systematic analyses of our dataset using contemporary baselines to detect and explain implicit hate speech, and we discuss key features that challenge existing models. This dataset will continue to serve as a useful benchmark for understanding this multifaceted issue.

Key facts. Cited by 216 papers in the map (data through 7 Oct 2026). Builds on 25 of its 77 references that are in the map. First posted on arXiv 11 Sep 2021.

Builds on

25 of 77 references.

References · 25

  1. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  2. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  3. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 724
  4. 2017Convolutional Sequence to Sequence Learningcited by 550
  5. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  6. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  7. 2019Predicting the Type and Target of Offensive Posts in Social Mediacited by 268
  8. 2018Large Scale Crowdsourcing and Characterization of Twitter Abusive Behaviorcited by 265
  9. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  10. 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 208
  11. 2018Hate Speech Dataset from a White Supremacy Forumcited by 196
  12. 2020A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Supportcited by 182
13 more
  1. 2017Deep Learning for Hate Speech Detection in Tweetscited by 180
  2. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  3. 2017Understanding Abuse: A Typology of Abusive Language Detection Subtaskscited by 115
  4. 2017Detecting Online Hate Speech Using Context Aware Modelscited by 72
  5. 2018Thou shalt not hate: Countering Online Hate Speechcited by 64
  6. 2020Demoting Racial Bias in Hate Speech Detectioncited by 62
  7. 2019A Just and Comprehensive Strategy for Using NLP to Address Online Abusecited by 49
  8. 2016Analyzing the Targets of Hate in Online Social Mediacited by 48
  9. 2017Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approachcited by 17
  10. 2021Lifelong Learning of Hate Speech Classification on Social Mediacited by 14
  11. 2016Predicting online extremism, content adopters, and interaction reciprocitycited by 10
  12. 2018Hateminers : Detecting Hate speech against Womencited by 5
  13. 2019Learning to Decipher Hate Symbolscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 23; 2023: 49; 2024: 54; 2025: 51; 2026: 38.

216 papers.

Sort:

By area:

  1. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  2. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  3. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  4. 2023Large Language Model Alignment: A Surveycited by 241
  5. 2023Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speechcited by 165
  6. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
  7. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  8. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 96
  9. 2024ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teamingcited by 96
  10. 2023Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Taskscited by 88
  11. 2023LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Codingcited by 64
  12. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 62
38 more
  1. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  2. 2022A Close Look into the Calibration of Pre-trained Language Modelscited by 57
  3. 2023Probing LLMs for hate speech detection: strengths and vulnerabilitiescited by 52
  4. 2023Unveiling the Implicit Toxicity in Large Language Modelscited by 51
  5. 2023Multi-lingual and Multi-cultural Figurative Language Understandingcited by 47
  6. 2023Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarkscited by 45
  7. 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreakscited by 45
  8. 2023Evaluating GPT-3 Generated Explanations for Hateful Content Moderationcited by 44
  9. 2023Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysiscited by 44
  10. 2022SafeText: A Benchmark for Exploring Physical Safety in Language Modelscited by 41
  11. 2023Decoding the Underlying Meaning of Multimodal Hateful Memescited by 38
  12. 2023Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Modelscited by 37
  13. 2023COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statementscited by 34
  14. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  15. 2023HARE: Explainable Hate Speech Detection with Step-by-Step Reasoningcited by 30
  16. 2023PREADD: Prefix-Adaptive Decoding for Controlled Text Generationcited by 29
  17. 2023Social Bias Probing: Fairness Benchmarking for Language Modelscited by 29
  18. 2024AI for social science and social science of AI: A Surveycited by 29
  19. 2023ToViLaG: Your Visual-Language Generative Model is Also An Evildoercited by 27
  20. 2023From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Modelscited by 26
  21. 2024Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Modelscited by 26
  22. 2022Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speechcited by 25
  23. 2024Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detectioncited by 25
  24. 2023An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Modelscited by 24
  25. 2022How Hate Speech Varies by Target Identity: A Computational Analysiscited by 23
  26. 2024MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Interventioncited by 20
  27. 2022Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitionscited by 18
  28. 2024Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languagescited by 18
  29. 2022Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalizationcited by 17
  30. 2024ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?cited by 17
  31. 2024Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiencycited by 17
  32. 2022ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detectioncited by 15
  33. 2024Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHFcited by 15
  34. 2022KOLD: Korean Offensive Language Datasetcited by 14
  35. 2023Watch Your Language: Investigating Content Moderation with Large Language Modelscited by 14
  36. 2023LifeTox: Unveiling Implicit Toxicity in Life Advicecited by 14
  37. 2024Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIFcited by 13
  38. 2025Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreementcited by 13

50 most cited of 216 All 216 (JSON)