CoChat

Quality of citation data using the natural language processing tool ChatGPT in rheumatology: creation of false references

Open access
Hueber, Axel J, Kleyer, Arnd · 2023 · RMD Open

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

Division of Rheumatology, Paracelsus Medical University, Klinikum Nürnberg, Nürnberg, Germany Department of Internal Medicine 3, Rheumatology and Immunology, FriedrichAlexanderUniversität ErlangenNürnberg and Universitätsklinikum Erlangen, Erlangen, Germany Deutsches Zentrum Immuntherapie, FriedrichAlexanderUniversität ErlangenNürnberg and Universitätsklinikum Erlangen, Erlangen, Germany

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1136/rmdopen-2023-003248

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 ChatGPT interaction following a request for an off-label use with ruxolitinib for a patient with eosinophilic fasciitis. Specific request for the literature sources (A), confrontation with its fictive source (B) (website retrieval 18 April 2023).
Figure 1 ChatGPT interaction following a request for an off-label use with ruxolitinib for a patient with eosinophilic fasciitis. Specific request for the literature sources (A), confrontation with its fictive source (B) (website retrieval 18 April 2023).CC BY-NC · PubMed Central

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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?

Self-check

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

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

Citations

Cites

Show all 3 references

Cited by

See all 26

Metadata

Authors
Hueber, A. J., & Kleyer, A.
Affiliations
Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
Corresponding author
Hueber, Axel J
Venue
RMD Open
Publisher
BMJ
Published
2023-06
Volume
9
Issue
2
Pages
e003248
ISSN
2056-5933 (ISSN-L)
OpenAlex
W4379645044
Cited by
16
References
3
Citations by year
2026: 3 · 2025: 2 · 2024: 7 · 2023: 4
FWCI
2.98
Type
journal article
Language
en
Open access
Locations
  • RMD Open (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • OPUS Repository (Kooperativer Bibliotheksverbund Berlin-Brandenburg) (submittedVersion, cc-by-nc)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Library and Information Sciences › scientometrics and bibliometrics research
  • Social Sciences › Library and Information Sciences › Academic Writing and Publishing
  • Social Sciences › Education › Academic integrity and plagiarism
Keywords
ChatGPT, AI-generated text, bibliographic references, natural language processing, AI hallucination
MeSH terms
Humans, Natural Language Processing, Rheumatology

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: Quality of citation data using the natural language processing tool ChatGPT in rheumatology: creation of false references. https://app.cochat.ai/papers/10.1136/rmdopen-2023-003248
The paper
Hueber, A. J., & Kleyer, A. (2023). Quality of citation data using the natural language processing tool ChatGPT in rheumatology: creation of false references. RMD Open. https://doi.org/10.1136/rmdopen-2023-003248

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.