ChatGPT fabricates references: the authors caught it inventing a non-existent 'Ribeiro and Vala, 2020' article with full bibliographic details¶
Claim · All claims
Evidence · 1 study · reviewr1·q1
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person · recheck by 2026: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q1 i? When asked for references on drawbacks, ChatGPT cited a 'Ribeiro and Vala, 2020' conference presentation that the authors' deep search found does not exist. → Baidoo-Anu 2023
Evidence¶
Baidoo-Anu 2023¶
Baidoo-Anu, D., & Owusu Ansah, L. (2023). Education in the Era of Generative Artificial Intelligence (AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning. Journal of AI, 7(1), 52-62. https://doi.org/10.61969/jai.1337500
q1 · i? · review · r1
The authors' own verification test: ChatGPT cited "Ribeiro and Vala, 2020" with full bibliographic details including a non-functional URL; the authors' search found no such presentation and concluded it was fabricated. Consistent with Qadir's (2022) report of a made-up article.
"Deep search for ‘Ribeiro and Vala, 2020’ work revealed that there is no conference presentation by Ribeiro and Vala, 2020 on generative artificial AI. Therefore, we have reasons to believe that this was fabricated article."
Discussion¶
Related Claims¶
- Of 178 reference sources produced by AI dialogue systems, 69 lacked a DOI and 28 could not be found via Google search and had no existing DOI — related
- ChatGPT-generated text shows inaccuracy, weak logical flow, lack of critical elaboration and non-originality in an author's first-hand test — related
- Gen-AI hallucinates sources and values and produces convincing but incorrect explanations, risking student misinformation — related
- AI-assisted scientific writing assignments risk fabricated references and altered chemical meaning — related
- AI-generated ethics exercise materials carried external citations that did not survive checking, ranging from misattributed to apparently fabricated — related
- The most frequently cited ethical concerns about GenAI in research were hallucinated facts, fabricated references, and misleading content — related
- Most of the article's body text was generated by ChatGPT from author prompts, and all references ChatGPT inserted were fictional — a broader claim this one bears on
- Review-attributed evidence: fabricated model-generated references clustered in disciplinary journals in a student verification exercise — related
- Students report negative experiences with ChatGPT including inaccurate outputs, lack of emotional connection, and risk of overreliance, which constrain competence — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
chatgpt-fabricates-references |
title |
ChatGPT fabricates references: the authors caught it inventing a non-existent 'Ribeiro and Vala, 2020' article with full bibliographic details |
description |
ChatGPT fabricates references: the authors caught it inventing a non-existent 'Ribeiro and Vala, 2020' article with full bibliographic details |
status |
review |
evidence_strength |
weak |
newest_evidence |
2023 |
recheck_by |
2026 |
generated |
by process:wiki-ingest on 2026-10-15 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — baidoo-anu-2023 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.