mlsanityData to 7 Oct 2026

NLP for Counterspeech against Hate: A Survey and How-To Guide

arXiv 2403.20103 ↗First posted 29 Mar 2024cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

In recent years, counterspeech has emerged as one of the most promising strategies to fight online hate. These non-escalatory responses tackle online abuse while preserving the freedom of speech of the users, and can have a tangible impact in reducing online and offline violence. Recently, there has been growing interest from the Natural Language Processing (NLP) community in addressing the challenges of analysing, collecting, classifying, and automatically generating counterspeech, to reduce the huge burden of manually producing it. In particular, researchers have taken different directions in addressing these challenges, thus providing a variety of related tasks and resources. In this paper, we provide a guide for doing research on counterspeech, by describing - with detailed examples - the steps to undertake, and providing best practices that can be learnt from the NLP studies on this topic. Finally, we discuss open challenges and future directions of counterspeech research in NLP.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 52 of its 126 references that are in the map. First posted on arXiv 29 Mar 2024.

Builds on

52 of 126 references.

References · 52

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  4. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  5. 2017Why We Need New Evaluation Metrics for NLGcited by 232
  6. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 215
  7. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  8. 2020Directions in Abusive Language Training Data: Garbage In, Garbage Outcited by 139
  9. 2019A Benchmark Dataset for Learning to Intervene in Online Hate Speechcited by 128
  10. 2017Understanding Abuse: A Typology of Abusive Language Detection Subtaskscited by 115
  11. 2019CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speechcited by 109
  12. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
38 more
  1. 2021Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speechcited by 81
  2. 2018Thou shalt not hate: Countering Online Hate Speechcited by 64
  3. 2020Generating Counter Narratives against Online Hate Speech: Data and Strategiescited by 58
  4. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  5. 2020Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspectivecited by 43
  6. 2022Handling and Presenting Harmful Text in NLP Researchcited by 43
  7. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  8. 2021Towards Knowledge-Grounded Counter Narrative Generation for Hate Speechcited by 41
  9. 2020Detecting East Asian Prejudice on Social Mediacited by 40
  10. 2020Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisiscited by 40
  11. 2022Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Counteringcited by 40
  12. 2023Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformationcited by 39
  13. 2021SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failurescited by 37
  14. 2018Neural Argument Generation Augmented with Externally Retrieved Evidencecited by 34
  15. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  16. 2022Hate Speech and Counter Speech Detection: Conversational Context Does Mattercited by 32
  17. 2022Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Studycited by 30
  18. 2022CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeechcited by 28
  19. 2023Benchmarking the Generation of Fact Checking Explanationscited by 25
  20. 2019Sentence-Level Content Planning and Style Specification for Neural Text Generationcited by 23
  21. 2021Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Modelcited by 23
  22. 2020Countering hate on social media: Large scale classification of hate and counter speechcited by 22
  23. 2021Argument Undermining: Counter-Argument Generation by Attacking Weak Premisescited by 22
  24. 2023Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Languagecited by 22
  25. 2023Understanding Counterspeech for Online Harm Mitigationcited by 17
  26. 2019Hope Speech Detection: A Computational Analysis of the Voice of Peacecited by 15
  27. 2021Generating Fluent Fact Checking Explanations with Unsupervised Post-Editingcited by 15
  28. 2023DisCGen: A Framework for Discourse-Informed Counterspeech Generationcited by 14
  29. 2021Empowering NGOs in Countering Online Hate Messagescited by 13
  30. 2023Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generationcited by 13
  31. 2021Countering Online Hate Speech: An NLP Perspectivecited by 12
  32. 2023ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speechcited by 12
  33. 2018Examining a hate speech corpus for hate speech detection and popularity predictioncited by 10
  34. 2021Multilingual Counter Narrative Type Classificationcited by 9
  35. 2022ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trollscited by 7
  36. 2023Characterizing and Predicting Social Correction on Twittercited by 7
  37. 2023Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularizationcited by 7
  38. 2023Which Argumentative Aspects of Hate Speech in Social Media can be reliably identified?cited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 8; 2026: 8.

21 papers.

Sort:

By area:

  1. 2024Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluationcited by 15
  2. 2024Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Counteringcited by 11
  3. 2024Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimizationcited by 4
  4. 2025Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theoriescited by 2
  5. 2025Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detectioncited by 2
  6. 2025Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Studycited by 2
  7. 2025Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxificationcited by 2
  8. 2025Capability Localization: Capabilities Can be Localized rather than Individual Knowledgecited by 1
  9. 2025HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigationcited by 1
  10. 2026Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Modelscited by 1
  11. 2026Multilingual Hate Speech Detection and Counterspeech Generation: A Comprehensive Survey and Practical Guidecited by 1
  12. 2026Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformationcited by 1
9 more
  1. 2024ViTHSD: Exploiting Hatred by Targets for Hate Speech Detection on Vietnamese Social Media Textscited by 0
  2. 2024Designing Human-AI Collaboration to Support Learning in Counterspeech Writingcited by 0
  3. 2025Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeechcited by 0
  4. 2025AIxcellent Vibes at GermEval 2025 Shared Task on Candy Speech Detection: Improving Model Performance by Span-Level Trainingcited by 0
  5. 2026Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Interventioncited by 0
  6. 2026CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchangescited by 0
  7. 2026Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeechcited by 0
  8. 2026Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generationcited by 0
  9. 2026Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeechcited by 0