arXiv cs.AI· Thomas H. Costello, Nathaniel Rabb, Michael Nicholas Stagnaro, Gordon Pennycook, David Rand·· 12 小时前AI 评分58
研究：用大语言模型多轮对话降低正在发酵的阴谋论信念
Reducing belief in conspiracy theories as they unfold using large language models
AI 导读
研究者在 2024 年 7 月特朗普遇刺未遂和 2025 年 9 月 Charlie Kirk 遇刺后数日内开展两项实验（N=472、N=1042），让持阴谋论观点的美国成年人与大语言模型进行多轮对话，结果显示其阴谋论信念相比对照组显著下降。对照组分别与 LLM 讨论无关话题或阅读静态事实清单；在一到两个月后的部分分析中，也观察到部分阴谋论信念下降的提示性证据。
正文 · 原文
Abstract:The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues with a large language model (LLM) can reduce belief in immediately unfolding conspiracies. In experiments conducted in the days following the July 2024 assassination attempt on Donald Trump and the September 2025 assassination of Charlie Kirk, U.S. adults (Experiment 1: N = 472; Experiment 2: N = 1042) holding conspiratorial views about the crisis event engaged in a multi-turn conversation with an LLM prompted to reduce their conspiracy belief. Compared to control participants who either discussed an irrelevant topic with an LLM or viewed a static fact sheet, participants in the LLM treatment showed significantly reduced conspiracy beliefs in both experiments. We also found some suggestive evidence of downstream effects of the LLM treatment, observing reduced belief in some -- but not all -- analyses of different conspiratorial beliefs one to two months later. These results shed light on the psychology of emerging conspiracies and highlight the potential for scalable, cognitively-focused interventions to counteract misinformation in the immediate aftermath of high-profile societal events.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.06151 [cs.HC] |
| (or arXiv:2608.06151v2 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2608.06151 arXiv-issued DOI via DataCite |
Submission history
From: Thomas Costello [view email]
[v1]
Thu, 6 Aug 2026 15:18:50 UTC (3,171 KB)
[v2]
Mon, 19 Oct 2026 19:25:08 UTC (3,256 KB)
来源：arXiv cs.AI · arxiv.org