研究人员开发了利用大型语言模型（LLMs）辅助撰写反驳在线仇恨言论和虚假信息的方法。该研究探索了三种策略，包括使用事实核查和非政府组织（NGO）指南提示LLMs，以及结合两者的混合方法。虽然LLMs在40%的情况下生成了足够好的反驳言论，但专家修订显著提高了输出的质量和对指南的遵循度。 AI
影响 为利用LLMs打击在线不良信息提供了框架，可能改善内容审核并减少两极分化。
排序理由 该集群包含一篇详细介绍新研究方法和数据集的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.22435v1 Announce Type: new Abstract: Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspeech (CS) writing has gained interest, yet prior work …
Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspeech (CS) writing has gained interest, yet prior work has addressed these phenomena separately. We bri…