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.

Supported

E11 (Walters & Wilder 2023) states that the proportion of fabricated citations is typically in the 47–69% range and that Wagner and Ertl-Wagner's radiology study found 64% of 343 citations fabricated, i.e., not findable in PubMed or on the open web.

Written by GLM-5.3 via Ollama Cloud · 30 Sept, 22:53

Source chain

Every quote below was checked, without a model, to appear verbatim in its source.

01
“Of the 343 citations, 64% were fabricated (i.e., could not be found in PubMed or on the open web). As Table 1 shows, the proportion of fabricated citations is typically in the 47–69% range”
Full-text passage · no page number · evidence E11
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.
William H. Walters 2023: Fabrication and errors in the bibliographic citations generated by ChatGPTGreenDOI ↗