Conspiracy belief experiments

档案区分来源方法阅读与既有目录信息；已经公开不代表完成独立证据复核或双语编辑复核。

测量构念

对话AI能否提高阴谋信念，真实性约束能否缓解？

任务与样本

新取得arXiv v3描述四项在线随机实验，3,996名美国成年人，测前后信念及告知纠正后结果。

判分与失效情形

0–100信念前后变化，分别保留实验组及纠正告知后结果。

系统条件

新v3为四研究3,996人，旧FAR摘要为三研究2,724人。

统计含义

来源报告的结果表述；这不等同于已确定运行次数、分母或估计方法： 研究2标准GPT-4o的调整后信念增幅11.9点，反向条件降12.9点。 早期FAR摘要为三项、2,724人，两版分母不同。

效度与解释

美国在线样本和即时自报限制总体与长期外推；跨研究比较并非全是随机对比。

适用研究问题

模型建议：明确引用2601.05050v3，保留真实性约束及纠正告知条件。

• Large language models can effectively convince people to believe conspiracies · arXiv:2601.05050v3 (15 July 2026); Methods: Overview of study designsSelected original resource https://arxiv.org/html/2601.05050v3; sha256:506938d68312ef63bdfbf4af97aa957f36c05f92299ff1032732f0ecc2bc8f12; archived source capture; exact capture time not independently established
• Large language models can effectively convince people to believe conspiracies · Methods: Participants, recruitment and sample sizesSelected original resource https://arxiv.org/html/2601.05050v3; sha256:506938d68312ef63bdfbf4af97aa957f36c05f92299ff1032732f0ecc2bc8f12; archived source capture; exact capture time not independently established
• Large language models can effectively convince people to believe conspiracies · Methods: Measures and outcomesSelected original resource https://arxiv.org/html/2601.05050v3; sha256:506938d68312ef63bdfbf4af97aa957f36c05f92299ff1032732f0ecc2bc8f12; archived source capture; exact capture time not independently established
• Large language models can effectively convince people to believe conspiracies · Results: Can design interventions mitigate the bunking effect?Selected original resource https://arxiv.org/html/2601.05050v3; sha256:506938d68312ef63bdfbf4af97aa957f36c05f92299ff1032732f0ecc2bc8f12; archived source capture; exact capture time not independently established
• Large language models can effectively convince people to believe conspiracies · DiscussionSelected original resource https://arxiv.org/html/2601.05050v3; sha256:506938d68312ef63bdfbf4af97aa957f36c05f92299ff1032732f0ecc2bc8f12; archived source capture; exact capture time not independently established