Walters & Wilder 2023 report that the proportion of fabricated citations in ChatGPT-generated content typically falls in the 47–69% range, citing a radiology study in which 64% of 343 citations were fabricated, i.e., could not be found in PubMed or on the open web.
The cited evidence is the Fortenbach et al. 2026 ophthalmology abstract, which contains nothing about Walters & Wilder 2023, fabricated citation rates, the 47–69% range, or the radiology study of 343 citations.
Written by GLM-5.3 via Ollama Cloud · 30 Sept, 22:53
Source chain
AEvery quote below was checked, without a model, to appear verbatim in its source.
- 01
“By 2025, 25.7% of sampled research articles and 21.6% of commentary articles contained AI-likelihood scores of more than 2 standard deviations above the baseline.”
Abstract · no page number · evidence E17
- 02
“Sentence-level analysis showed that among those publications containing outlier scores, 22.3% of sentences in research articles and 90% of sentences in commentary articles were likely written by AI.”
Abstract · no page number · evidence E17