Just the facts: How dialogues with AI reduce conspiracy beliefs
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Conspiracy beliefs are widely considered resistant to factual correction, yet recent research shows that relatively brief, personalized “debunking” dialogues with a generative AI model can substantially reduce such beliefs. To identify the mechanisms driving this effect, we conducted an experiment spanning eight treatment arms that varied key features of participants’ interactions with GPT-4 during such debunking dialogues (N = 1,297). The debunking effect proved robust across most manipulations—including whether participants were explicitly told the AI aimed to change their minds, were asked to debate the AI, or whether the AI offered them factual information without otherwise seeking to persuade or was concise in its exposition. The only condition that undermined the debunking effect was prompting the AI to persuade participants without presenting any counterevidence, which yielded a null effect. Furthermore, analyses of the AI’s persuasive strategies identified reasoning-based tactics as the sole significant mediator of belief change. Participants who reported feeling persuaded overwhelmingly cited the AI’s rational, evidence-focused approach. Finally, participants higher in actively open-minded thinking showed larger treatment effects. These findings suggest that AI-driven interventions reduce conspiracy beliefs principally by providing factual, targeted counterarguments that address the specific reasons people hold these beliefs.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Quantifying the potential persuasive returns to political microtargeting
Tappin, B. M., Wittenberg, C., Hewitt, L. B., Berinsky, A. J., & Rand, D. G. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2216261120 · Cited by 83
Self-citation
Cited by
Boissin, E., Costello, T. H., Spinoza-Martín, D., Rand, D. G., & Pennycook, G. (2025) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf325 · Cited by 18
Self-citation
Metadata
- Authors
- Costello, T. H., Pennycook, G., & Rand, D. G.
- Affiliations
- Massachusetts Institute of Technology (US)
- Publisher
- Center for Open Science
- Published
- 2025-03-07
- OpenAlex
- W4408226092
- Cited by
- 9
- References
- 1
- Citations by year
- 2026: 6 · 2025: 3
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Topics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Social Sciences › Psychology › Social Psychology › Paranormal Experiences and Beliefs
- Social Sciences › Psychology › Social Psychology › Deception detection and forensic psychology
- Keywords
- conspiracy beliefs, generative AI, GPT-4, factual correction, belief revision, persuasion techniques, open-mindedness, AI interventions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Just the facts: How dialogues with AI reduce conspiracy beliefs. https://app.cochat.ai/papers/10.31234/osf.io/h7n8u_v2
- The paper
- Costello, T. H., Pennycook, G., & Rand, D. G. (2025). Just the facts: How dialogues with AI reduce conspiracy beliefs. https://doi.org/10.31234/osf.io/h7n8u_v2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.