研究：与聊天机器人对话七分钟可减少阴谋论信念
原标题：Seven minutes with a chatbot beat a fact sheet at reducing conspiracy beliefs in two experiments
AI 摘要
卡内基梅隆大学、MIT 和康奈尔大学的研究人员通过两项在线实验发现，与大型语言模型进行约七分钟的对话，能有效降低参与者对近期阴谋论的信念，效果优于静态事实清单，并能延续到数周后的新事件。研究使用 GPT-4o 筛选参与者，用 Google Gemini 进行对话，针对特朗普遇刺和 Kirk 遇害事件构建事实库，模型根据证据可用性调整说服策略。该研究展示了 LLM 在危机后纠正错误信息的潜力，但也提示了反向说服的风险。
正文节选
Seven minutes with a chatbot beat a fact sheet at reducing conspiracy beliefs in two experiments A brief conversation with a language model can reduce conspiracy beliefs right after a crisis, even when hard evidence is thin on the ground. The effect carries over to new events weeks later, according to researchers. Within a week of the assassination attempt on Donald Trump in July 2024, about half of a representative US sample had heard the event was staged. Eleven percent believed it. After the