Fabrication and errors in the bibliographic citations generated by ChatGPT.

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.

The impact of free access to the scientific literature: a review of recent research.

OBJECTIVES: The paper reviews recent studies that evaluate the impact of free access (open access) on the behavior of scientists as authors, readers, and citers in developed and developing nations. It also examines the extent to which the biomedical literature is used by the general public. METHOD: The paper is a critical review of the literature, with systematic description of key studies. RESULTS: Researchers report that their access to the scientific literature is generally good and improving. For authors, the access status of a journal is not an important consideration when deciding where to publish. There is clear evidence that free access increases the number of article downloads, although its impact on article citations is not clear. Recent studies indicate that large citation advantages are simply artifacts of the failure to adequately control for confounding variables. The effect of free access on the general public's use of the primary medical literature has not been thoroughly evaluated. CONCLUSIONS: Recent studies provide little evidence to support the idea that there is a crisis in access to the scholarly literature. Further research is needed to investigate whether free access is making a difference in non-research contexts and to better understand the dissemination of scientific literature through peer-to-peer networks and other informal mechanisms.

Disciplinary perspectives on later-life migration in the core journals of social gerontology.

PURPOSE: The authors examine the bibliographic structure of recent research on later-life migration, highlighting the contributions of particular journals and disciplines. DESIGN AND METHODS: The authors identify the primary journals publishing research in this area, including a set of four core journals within the field of social gerontology. They evaluate the disciplinary affiliations of authors publishing in the core journals and the extent to which those journals cite relevant research published elsewhere. RESULTS: Geographical and economic perspectives on later-life migration are underrepresented within the core journals of social gerontology. In particular, major articles published outside the core journals are seldom cited within those journals. IMPLICATIONS: Although the core journals of social gerontology account for over a third of the recent literature on later-life migration, they present only a partial (chiefly sociological) perspective on the subject.