CoChat

Generative AI as a tool for truth

Open access
Bago, Bence, Bonnefon, Jean-François · 2024 · Science

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Abstract

Conversation with a trained chatbot can reduce conspiratorial beliefs

Overview

CoChat Summary

## TL;DR

The paper’s abstract states that conversation with a trained chatbot can reduce conspiratorial beliefs. No further details of the intervention, sample, or effect size are provided in the supplied text.

## Key findings

  • The abstract’s main claim is that “conversation with a trained chatbot can reduce conspiratorial beliefs.”
  • The paper is a 2-page Science article (pp. 1164–1165) in volume 385, issue 6714.
  • The supplied text does not report any numerical effect sizes, sample sizes, or statistical results.

## Methods

  • Not stated in the paper.
  • The record identifies the piece as a journal article in *Science* (2024), but the provided text does not describe the study design, data, or analysis.
  • No sample, chatbot specification, or measurement procedure is described in the supplied text.

## Limitations

  • Not stated in the paper.
  • Evident from the supplied text: the record includes only the bibliographic entry and abstract, so the underlying methods, sample characteristics, and results are not available here.
  • Evident from the supplied text: no limitations or caveats are reported in the provided text.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1126/science.ads0433

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 0 Not valid · 0 Not checked · 1 Own results and interpretations

Show all 1 claims

Citations

Cites

Research works printed but not linked: 5

  1. V. Capraro , Proc. Natl. Acad. Sci. U.S.A. Nexus 3, pgae191 (2024).
  2. S. Y. Shin, J. Lee, Digit. Journal. 10, 412 (2022).
  3. A. Simchon, M. Edwards, S. Lewandowsky, Proc. Natl. Acad. Sci. U.S.A. Nexus 3, pgae035 (2024).
  4. B. Bago, D. G. Rand, G. Pennycook, Proc. Natl. Acad. Sci. U.S.A. Nexus 2, pgad100 (2023).
  5. V. Swami, M. Voracek, S. Stieger, U. S. Tran, A. Furnham, Cognition 133, 572 (2014).

Metadata

Authors
Bago, B., & Bonnefon, J.-F.
Affiliations
  • Department of Social Psychology, Tilburg University, Tilburg, Netherlands.
  • Centre National de la Recherche Scientifique (FR)
Venue
Science
Published
2024-09-13
Volume
385
Issue
6714
Pages
1164-1165
ISSN
  • 0036-8075 (ISSN-L)
  • 1095-9203
OpenAlex
W4402474855
Cited by
13
References
8
Citations by year
2026: 6 · 2025: 7
Type
journal article
Language
en
Licence
other-oa
Locations
  • Science (publishedVersion)
  • Research portal (Tilburg University) (publishedVersion, other-oa)
  • PubMed (publishedVersion)
  • HAL (submittedVersion)
Funders
Agence Nationale de la Recherche (ANR-17-EURE-0010, ANR-19-P3IA-0004)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Social Sciences › Psychology › Social Psychology › Deception detection and forensic psychology
Keywords
generative AI, chatbots, conspiracy beliefs, misinformation
MeSH terms
Artificial Intelligence, Communication, Humans

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.

A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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

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.