In the context of escalating hate speech and polarization on social media, this study investigates the potential of employing responses generated by Large Language Models (LLM), complemented with pertinent verified knowledge links, to counteract such trends. Through extensive A/B testing involving the posting of 753 automatically generated responses, the goal was to minimize the propagation of hate speech directed at Ukrainian refugees in Poland. The results indicate that deploying LLM-generated responses as replies to harmful tweets effectively diminishes user engagement, as measured by likes/impressions. When we respond to an original tweet, i.e., which is not a reply, we reduce the engagement of users by over 20\% without increasing the number of impressions. On the other hand, our responses increase the ratio of the number of replies to a harmful tweet to impressions, especially if the harmful tweet is not original. Additionally, the study examines how generated responses influence the overall sentiment of tweets in the discussion, revealing that our intervention does not significantly alter the mean sentiment. This paper suggests the implementation of an automatic moderation system to combat hate speech on social media and provides an in-depth analysis of the A/B experiment, covering methodology, data collection, and statistical outcomes. Ethical considerations and challenges are also discussed, offering guidance for the development of discourse moderation systems leveraging the capabilities of generative AI.

翻译：在社交媒体上仇恨言论与两极分化日益加剧的背景下，本研究探讨了利用大型语言模型（LLM）生成的回应，并补充相关可验证知识链接，以对抗此类趋势的潜力。通过涉及753条自动生成回帖的大规模A/B测试，目标是最小化针对波兰乌克兰难民的仇恨言论传播。结果表明，将LLM生成的回应部署为有害推文的回复，能有效降低用户参与度（以点赞/曝光量衡量）。当我们回复原始推文（即非回复性推文）时，用户参与度降低超过20%，且未增加曝光量；另一方面，我们的回应提高了有害推文回复数与曝光量的比率，尤其当有害推文非原始帖子时。此外，研究考察了生成回应如何影响讨论中推文的整体情感倾向，发现干预措施并未显著改变平均情感值。本文建议实施自动审核系统以打击社交媒体上的仇恨言论，并提供了包括方法、数据收集和统计结果的A/B实验深度分析。同时讨论了伦理考量和挑战，为开发基于生成式AI能力的对话审核系统提供了指导。