# On Zero-Shot Counterspeech Generation by LLMs

arXiv: https://arxiv.org/abs/2403.14938 · HTML: https://mlsanity.com/paper/2403.14938/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [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)
- [Dialogue Response Ranking Training with Large-Scale Human Feedback Data](https://mlsanity.com/paper/2009.06978/) (2020)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020)
- [Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks](https://mlsanity.com/paper/1802.05758/) (2018)
- [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)
- [Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation](https://mlsanity.com/paper/2112.07924/) (2021)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [Multilingual Counter Narrative Type Classification](https://mlsanity.com/paper/2109.13664/) (2021)

## Built on by (most cited first, 17 of 17)

- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation](https://mlsanity.com/paper/2406.15227/) (2024)
- [CrowdCounter: A benchmark type-specific multi-target counterspeech dataset](https://mlsanity.com/paper/2410.01400/) (2024)
- [Assessing the Human Likeness of AI-Generated Counterspeech](https://mlsanity.com/paper/2410.11007/) (2024)
- [Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization](https://mlsanity.com/paper/2412.15453/) (2024)
- [CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs](https://mlsanity.com/paper/2501.17581/) (2025)
- [MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation](https://mlsanity.com/paper/2502.11246/) (2025)
- [Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation](https://mlsanity.com/paper/2507.07307/) (2025)
- [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)
- [Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate](https://mlsanity.com/paper/2506.04043/) (2025)
- [HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation](https://mlsanity.com/paper/2507.04350/) (2025)
- [Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text](https://mlsanity.com/paper/2510.03683/) (2025)
- [Multilingual Hate Speech Detection and Counterspeech Generation: A Comprehensive Survey and Practical Guide](https://mlsanity.com/paper/2603.19279/) (2026)
- [Designing Human-AI Collaboration to Support Learning in Counterspeech Writing](https://mlsanity.com/paper/2410.03032/) (2024)
- [Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses](https://mlsanity.com/paper/2508.15855/) (2025)
- [Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets](https://mlsanity.com/paper/2510.16359/) (2025)

## Abstract (arXiv)

With the emergence of numerous Large Language Models (LLM), the usage of such models in various Natural Language Processing (NLP) applications is increasing extensively. Counterspeech generation is one such key task where efforts are made to develop generative models by fine-tuning LLMs with hatespeech - counterspeech pairs, but none of these attempts explores the intrinsic properties of large language models in zero-shot settings. In this work, we present a comprehensive analysis of the performances of four LLMs namely GPT-2, DialoGPT, ChatGPT and FlanT5 in zero-shot settings for counterspeech generation, which is the first of its kind. For GPT-2 and DialoGPT, we further investigate the deviation in performance with respect to the sizes (small, medium, large) of the models. On the other hand, we propose three different prompting strategies for generating different types of counterspeech and analyse the impact of such strategies on the performance of the models. Our analysis shows that there is an improvement in generation quality for two datasets (17%), however the toxicity increase (25%) with increase in model size. Considering type of model, GPT-2 and FlanT5 models are significantly better in terms of counterspeech quality but also have high toxicity as compared to DialoGPT. ChatGPT are much better at generating counter speech than other models across all metrics. In terms of prompting, we find that our proposed strategies help in improving counter speech generation across all the models.