Metraipolis › archive › dc_6de81aa2aeaa

Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs — arXiv:2611.05572

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05572
License (as archived)
CC0-1.0
Archived
2026-11-05T18:17:25.291Z
SHA-256 of the archived text
effd479e776eddf672095cbaafb9a684cce3e1e71af3b7e78959e26c926e17fd
Stable URL of this page
https://metraipolis.com/documento/dc_6de81aa2aeaa

How to cite

Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs — arXiv:2611.05572 — arXiv (en), https://arxiv.org/abs/2611.05572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6de81aa2aeaa (Metraipolis archive dc_6de81aa2aeaa, sha256 effd479e776eddf672095cbaafb9a684cce3e1e71af3b7e78959e26c926e17fd)
BibTeX
@misc{dc6de81aa2aeaa,
  title = {Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs — arXiv:2611.05572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6de81aa2aeaa; sha256 effd479e776eddf672095cbaafb9a684cce3e1e71af3b7e78959e26c926e17fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.05572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:12:49.028Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).