CoChat
Sign Up
Cited by 18Misinformation and Its ImpactsAcademic integrity and plagiarismAcademic Publishing and Open Access

Does ChatGPT Ignore Article Retractions and Other Reliability Concerns?

Open access
Thelwall, Mike, Lehtisaari, Marianna, Katsirea, Irini, Holmberg, Kim, Zheng, Er‐Te·2025·Learned Publishing
DOI 10.1002/leap.2018
Open this paper in CoChat — free accountOpen PDF

Abstract

Large language models (LLMs) like ChatGPT seem to be increasingly used for information seeking and analysis, including to support academic literature reviews. To test whether the results might sometimes include retracted research, we identified 217 retracted or otherwise concerning academic studies with high altmetric scores and asked ChatGPT 4o‐mini to evaluate their quality 30 times each. Surprisingly, none of its 6510 reports mentioned that the articles were retracted or had relevant errors, and it gave 190 relatively high scores (world leading, internationally excellent, or close). The 27 articles with the lowest scores were mostly accused of being weak, although the topic (but not the article) was described as controversial in five cases (e.g., about hydroxychloroquine for COVID‐19). In a follow‐up investigation, 61 claims were extracted from retracted articles from the set, and ChatGPT 4o‐mini was asked 10 times whether each was true. It gave a definitive yes or a positive response two‐thirds of the time, including for at least one statement that had been shown to be false over a decade ago. The results therefore emphasise, from an academic knowledge perspective, the importance of verifying information from LLMs when using them for information seeking or analysis.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1002/leap.2018

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Generative AI chatbots may use and surface references to scientific research without disclosing their retracted status, including references to Riordan et al. and Patil et al.

    “While these chatbots can be trained to identify and warn users about retracted articles, they may also use and surface references to scientific research without disclosing their retracted status.9,30,31 This includes references to Riordan et al. and Patil et al. without disclosing that they have been retracted (see Figures 1-3).”

    From Why retracted articles can have an influential afterlife—and what to do about it (2026) · cites this paper as [30]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

2 retracted

Flagged first, then by citations

Research works printed but not linked: 2

  1. Brown, N. 2023. "Bots Behaving Badly: Products Liability Approach to Chatbot-Generated Defamation." Journal of Free Speech Law 3, no. 2: 389-424.
  2. Zheng, E., H. Z. Fu, and Z. Fang. 2024. "Can ChatGPT Predict Article Retraction Based on Twitter Mentions?" ArXiv Preprint arXiv:2403.16851. · arXiv

Cited by

Sorted by citations

Related

Authors
Thelwall, M., Lehtisaari, M., Katsirea, I., Holmberg, K., & Zheng, E.
Affiliations
  • University of Sheffield (GB)
  • University of Turku (FI)
Corresponding author
Thelwall, Mike
ORCID
Venue
Learned Publishing
Publisher
Wiley
Published
2025-08-04
Volume
38
Issue
4
ISSN
  • 0953-1513 (ISSN-L)
  • 1741-4857
DOI
10.1002/leap.2018
OpenAlex
W4412942230
Cited by
18
References
39
Citations by year
2026: 15 · 2025: 3
FWCI
31.14
Type
journal article
Language
en
Open access
Licence
Locations
  • Learned Publishing (publishedVersion, cc-by)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
  • UTUPub (University of Turku) (submittedVersion)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Social Sciences › Safety Research › Academic integrity and plagiarism
  • Social Sciences › Decision Sciences › Information Systems and Management › Academic Publishing and Open Access
Keywords
ChatGPT, large language models, retraction, retracted research, altmetrics, fact-checking, LLM reliability, misinformation, hydroxychloroquine, COVID-19 pandemic

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