ArticleScientific reports2023
Fabrication and errors in the bibliographic citations generated by ChatGPT.
Article in Scientific reports, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 109 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
109 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Pooled it
- Large language models in ophthalmology: promise, peril, and the urgent need for guardrails.Eye (London, England) · 2026Article
- Telling Students to Evaluate Does Not Make It Happen: Task Stage, Offloading Tendency, and Error Detection in AI-Assisted Student Writing.Behavioral sciences (Basel, Switzerland) · 2026Article
- Large language models answering structured questions on external cervical resorption: a comparative study.Odontology · 2026Article
- Reference quality of OpenEvidence across five medical specialties.npj health systems · 2026Article
- A practical risk framework for large language model use in life science research.PLoS computational biology · 2026Article
- Illusions of Understanding from Outsourcing Thinking to LLMs.Computational brain & behavior · 2026Article
- Authors, reviewers, editors… smitten and bitten by the artificial intelligence (AI) bug!Indian journal of anaesthesia · 2026Article
- Fabricated references are twice as common in medRxiv preprints as in peer-reviewed articles.Journal of internal medicine · 2026Article
- Accuracy and Error Patterns of References Generated by Large Language Models in Endodontics: The Role of Prompt Design and Model Selection.Medical science monitor : international medical journal of experimental and clinical research · 2026Article
- Teaching the Atomic Sentence Method for Source-Verified, AI-Assisted Literature Synthesis to Clinical Health Care Professionals: Single-Cohort Feasibility and Acceptability Study.JMIR formative research · 2026Article
- Leveraging generative artificial intelligence errors to teach appropriate citation usage.Journal of microbiology & biology education · 2026Article
- Using journal article annotations with Zotero to improve scientific literacy in course-based undergraduate research experiences.Journal of microbiology & biology education · 2026Article
- Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study.JMIR medical education · 2026Article
- Provenance, Not Prohibition: A Framework for AI in Scholarly Publishing.Laryngoscope investigative otolaryngology · 2026Article
- Comparative evaluation of artificial intelligence-assisted literature search tools for identifying clinically meaningful evidence in cardiology.European heart journal. Digital health · 2026Article
- GeneKnow: An auditable AI framework for source-grounded biological evidence synthesis.bioRxiv : the preprint server for biology · 2026Article
- AI-enabled clinical decision support in breast cancer care: a blinded multicenter benchmarking study comparing medically specialized with a general-purpose system.Journal of medical systems · 2026Article
- Reply: Evaluating the reference accuracy of large language models in radiology: a comparative study across subspecialties.Diagnostic and interventional radiology (Ankara, Turkey) · 2026Article
- Letter to the Editor: Rethinking reference accuracy in large language models for radiology.Diagnostic and interventional radiology (Ankara, Turkey) · 2026Article
49 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Although chatbots such as ChatGPT can facilitate cost-effective text generation and editing, factually incorrect responses (hallucinations) limit their utility. This study evaluates one particular type of hallucination: fabricated bibliographic citations that do not represent actual scholarly works. We used ChatGPT-3.5 and ChatGPT-4 to produce short literature reviews on 42 multidisciplinary topics, compiling data on the 636 bibliographic citations (references) found in the 84 papers. We then searched multiple databases and websites to determine the prevalence of fabricated citations, to identify errors in the citations to non-fabricated papers, and to evaluate adherence to APA citation format. Within this set of documents, 55% of the GPT-3.5 citations but just 18% of the GPT-4 citations are fabricated. Likewise, 43% of the real (non-fabricated) GPT-3.5 citations but just 24% of the real GPT-4 citations include substantive citation errors. Although GPT-4 is a major improvement over GPT-3.5, problems remain.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.