Dialogues with Large Language Models Reduce Conspiracy Beliefs Even When the AI Is Perceived as Human

Abstract

Although conspiracy beliefs are often viewed as resistant to correction, recent evidence shows that personalized, fact-based dialogues with a large language model (LLM) can reduce them. Is this effect driven by the debunking facts and evidence, or does it rely on the messenger being an AI? In other words, would the same message be equally effective if delivered by a human? To answer this question, we conducted a preregistered experiment (N = 955) in which participants reported either a conspiracy belief or a nonconspiratorial but epistemically unwarranted belief and interacted with a LLM that argued against that belief using facts and evidence. We randomized whether the debunking LLM was characterized as an AI tool or a human expert and whether the model used human-like conversational tone. The conversations significantly reduced participants' confidence in both conspiracies and epistemically unwarranted beliefs, with no significant differences across conditions. Thus, AI persuasion is not reliant on the messenger being an AI model: it succeeds by generating compelling messages.

The authors' own abstract, copied from pubmed.ncbi.nlm.nih.gov.

How to cite it

Built from the details listed on this page. Check them against the paper before you submit.

Boissin, E., Costello, T. H., Spinoza-Martín, D., Rand, D. G., & Pennycook, G. (2025). Dialogues with Large Language Models Reduce Conspiracy Beliefs Even When the AI Is Perceived as Human. PNAS Nexus (peer-reviewed). https://doi.org/10.1093/pnasnexus/pgaf325

Boissin, Esther, et al. "Dialogues with Large Language Models Reduce Conspiracy Beliefs Even When the AI Is Perceived as Human." PNAS Nexus (peer-reviewed), 2025, https://doi.org/10.1093/pnasnexus/pgaf325.

@article{boissin2025dialogues,
  title = {Dialogues with Large Language Models Reduce Conspiracy Beliefs Even When the AI Is Perceived as Human},
  author = {Esther Boissin and Thomas H. Costello and Daniel Spinoza-Martín and David G. Rand and Gordon Pennycook},
  journal = {PNAS Nexus (peer-reviewed)},
  year = {2025},
  url = {https://doi.org/10.1093/pnasnexus/pgaf325},
}

What it is

Preregistered experiment (N = 955) in PNAS Nexus testing whether LLM debunking works because the messenger is an AI. Conversations reduced confidence in conspiracy and other unwarranted beliefs whether the model was framed as an AI tool or a human expert.

Topics