LLM generated responses to mitigate the impact of hate speech

TL;DR

This paper demonstrates that LLM-generated responses can effectively reduce user engagement with hate speech on social media, showing promise for automated moderation but raising ethical concerns.

Contribution

First real-life A/B test evaluating LLM-generated counter-speech effectiveness in reducing hate speech engagement on social media.

Findings

LLM responses decrease user engagement by over 20%.

Interventions are particularly effective for tweets with at least ten views.

Proposes a simple metric for measuring user engagement.

Abstract

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.