# Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study

arXiv: https://arxiv.org/abs/2204.01440 · HTML: https://mlsanity.com/paper/2204.01440/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)
- [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://mlsanity.com/paper/1907.12461/) (2019)
- [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://mlsanity.com/paper/1908.06083/) (2019)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://mlsanity.com/paper/1910.03270/) (2019)
- [Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech](https://mlsanity.com/paper/2107.08720/) (2021)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020)
- [Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective](https://mlsanity.com/paper/2012.12305/) (2020)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech](https://mlsanity.com/paper/2106.11783/) (2021)
- [Like trainer, like bot? Inheritance of bias in algorithmic content moderation](https://mlsanity.com/paper/1707.01477/) (2017)
- [DeepHate: Hate Speech Detection via Multi-Faceted Text Representations](https://mlsanity.com/paper/2103.11799/) (2021)

## Built on by (most cited first, 30 of 30)

- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements](https://mlsanity.com/paper/2306.01985/) (2023)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [Understanding Counterspeech for Online Harm Mitigation](https://mlsanity.com/paper/2307.04761/) (2023)
- [On Zero-Shot Counterspeech Generation by LLMs](https://mlsanity.com/paper/2403.14938/) (2024)
- [Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation](https://mlsanity.com/paper/2412.07338/) (2024)
- [Outcome-Constrained Large Language Models for Countering Hate Speech](https://mlsanity.com/paper/2403.17146/) (2024)
- [Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering](https://mlsanity.com/paper/2410.03466/) (2024)
- [HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models](https://mlsanity.com/paper/2310.13985/) (2023)
- [Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization](https://mlsanity.com/paper/2309.02311/) (2023)
- [Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation](https://mlsanity.com/paper/2403.09159/) (2024)
- [Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?](https://mlsanity.com/paper/2305.15908/) (2023)
- [A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models](https://mlsanity.com/paper/2402.11676/) (2024)
- [A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation](https://mlsanity.com/paper/2406.15227/) (2024)
- [Decoding Hate: Exploring Language Models' Reactions to Hate Speech](https://mlsanity.com/paper/2410.00775/) (2024)
- [Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi](https://mlsanity.com/paper/2402.07262/) (2024)
- [Assessing the Human Likeness of AI-Generated Counterspeech](https://mlsanity.com/paper/2410.11007/) (2024)
- [Echoes of Discord: Forecasting Hater Reactions to Counterspeech](https://mlsanity.com/paper/2501.16235/) (2025)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Automatic Evaluation of Generative Models with Instruction Tuning](https://mlsanity.com/paper/2310.20072/) (2023)
- [CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs](https://mlsanity.com/paper/2501.17581/) (2025)
- [Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models](https://mlsanity.com/paper/2406.07288/) (2024)
- [PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset](https://mlsanity.com/paper/2501.00697/) (2025)
- [Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories](https://mlsanity.com/paper/2504.16604/) (2025)
- [Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Study](https://mlsanity.com/paper/2506.11919/) (2025)
- [Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation](https://mlsanity.com/paper/2510.12316/) (2025)
- [Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence](https://mlsanity.com/paper/2309.00751/) (2023)
- [Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech](https://mlsanity.com/paper/2508.04638/) (2025)
- [Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation](https://mlsanity.com/paper/2604.17020/) (2026)
- [Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech](https://mlsanity.com/paper/2607.26236/) (2026)

## Abstract (arXiv)

In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English. We first present a comparative study to determine whether there is a particular Language Model (or class of LMs) and a particular decoding mechanism that are the most appropriate to generate CNs. Findings show that autoregressive models combined with stochastic decodings are the most promising. We then investigate how an LM performs in generating a CN with regard to an unseen target of hate. We find out that a key element for successful `out of target' experiments is not an overall similarity with the training data but the presence of a specific subset of training data, i.e. a target that shares some commonalities with the test target that can be defined a-priori. We finally introduce the idea of a pipeline based on the addition of an automatic post-editing step to refine generated CNs.