arXiv cs.AI· Thomas H. Costello, Gordon Pennycook, David G. Rand·· 12 小时前AI 评分58
研究：与 AI 对话如何降低阴谋论信念
Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs
AI 导读
一项针对美国成年人的两项实验（总 N=2193）发现，与 AI 的个性化对话能显著降低阴谋论信念。研究逐一排除了披露 AI 的说服目标、将对话框定为辩论、要求 AI 只告知不说服、将回复长度减半、改变信念测量方式、用单条定制消息替代对话等因素，效果依然稳健；只有要求 AI 在没有事实证据和论证的情况下说服，才会明显削弱效果。
正文 · 原文
Abstract:Personalized dialogues with AI substantially reduce conspiracy beliefs. To identify why, we conducted two experiments with U.S. adults recruited online (total N = 2,193) that removed possible causes one at a time. The debunking effect was robust to disclosing the AI's persuasive goal, framing the exchange as a debate, instructing the AI to inform rather than persuade, halving its response length, altering how beliefs were measured, and replacing the dialogue with a single tailored message. Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect. Content analyses of the AI's output and participants' own accounts linked larger reductions in conspiracy beliefs to factual argumentation rather than rapport, storytelling, or appeals to empathy. AI dialogues appear to reduce conspiracy beliefs primarily by supplying relevant, well-reasoned counterevidence. Our results suggest that humans might be similarly effective if they could supply comparable evidence.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05572 [cs.HC] |
| (or arXiv:2611.05572v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05572 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Thomas Costello [view email]
[v1]
Tue, 3 Nov 2026 20:03:55 UTC (3,858 KB)
来源：arXiv cs.AI · arxiv.org