cs.HCNov 3, 2026

Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs

Authors: Thomas H. Costello, Gordon Pennycook, David G. Rand

Organizations: Department of Social and Decision Sciences, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Psychology, Cornell University, Ithaca, NY, USA · Department of Information Science, Cornell University, Ithaca, NY, USA · Marketing and Management Communications, SC Johnson School of Business, Cornell University, Ithaca, NY, USA · 

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.

Explore similar work

CardsList
  1. Large language models can effectively convince people to believe conspiracies

    Jan 8, 2026Thomas H. Costello, Kellin Pelrine, Matthew Kowal +6Deception in Language ModelsLLM Safety

  2. Reducing belief in conspiracy theories as they unfold using large language models

    Aug 6, 2026Thomas H. Costello, Nathaniel Rabb, Michael Nicholas Stagnaro +2Belief RevisionConversational Agents

  3. A misinformation playbook sharpens judgement without breeding cynicism

    Oct 15, 2026Tong Guo, Teng Ye, Yutong Xie +1Fake News Detection