# LLM generated responses to mitigate the impact of hate speech

arXiv: https://arxiv.org/abs/2311.16905 · HTML: https://mlsanity.com/paper/2311.16905/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2023.

## Built on by (most cited first, 7 of 7)

- [What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma](https://mlsanity.com/paper/2505.12727/) (2025)
- [LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation](https://mlsanity.com/paper/2503.07237/) (2025)
- [CHASM: Unveiling Covert Advertisements on Chinese Social Media](https://mlsanity.com/paper/2604.20511/) (2026)
- [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)
- [Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots](https://mlsanity.com/paper/2603.01942/) (2026)
- [Beyond Benchmarks: Exposing the Hidden Crisis in Bangla Hate Speech Detection](https://mlsanity.com/paper/2607.11597/) (2026)
- [Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation](https://mlsanity.com/paper/2608.23152/) (2026)

## Abstract (arXiv)

In this study, we explore the use of Large Language Models (LLMs) to counteract hate speech. We conducted the first real-life A/B test assessing the effectiveness of LLM-generated counter-speech. During the experiment, we posted 753 automatically generated responses aimed at reducing user engagement under tweets that contained hate speech toward Ukrainian refugees in Poland. Our work shows that interventions with LLM-generated responses significantly decrease user engagement, particularly for original tweets with at least ten views, reducing it by over 20%. This paper outlines the design of our automatic moderation system, proposes a simple metric for measuring user engagement and details the methodology of conducting such an experiment. We discuss the ethical considerations and challenges in deploying generative AI for discourse moderation.