EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluating AI-Generated Citation Accuracy: An Empirical Framework and Verification Efficiency Matrix for Academic Librarians

Karan Jaiswal, Anurag Kumar

Academic Research Journal of Science and Technology (ARJST) · 01.06.2026 · 5 (03) · 1-10

DOI: 10.63300/arjst0503062026.01 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Research Journal of Science and Technology (ARJST), online erschienen am 01.06.2026. Verfasst von Karan Jaiswal und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Using the widespread adoption of Generative AI tools, there is a risk of “Reference Hallucination” which threatens academic integrity. This study evaluates the structural correctness of citations generated by Large Language Models (LLMs) and presents an empirical verification matrix for academic librarians. The study investigates the hallucination rate and maps the verification efficiency of traditional databases (Scopus, JSTOR) against search-augmented AI tools (Elicit, Perplexity) through the analysis of a 100 AI-generated citation simulation matrix across four multidisciplinary fields.. The findings suggest a “Verify-and-Validate” structure workflow using the SIFT method to reduce the invisible workload on the library services.

Zitieren

APA

Jaiswal, K., & Kumar, A. (2026). Evaluating AI-Generated Citation Accuracy: An Empirical Framework and Verification Efficiency Matrix for Academic Librarians. Academic Research Journal of Science and Technology (ARJST), 5(03), 1-10. https://doi.org/10.63300/arjst0503062026.01

Vancouver

Jaiswal K, Kumar A. Evaluating AI-Generated Citation Accuracy: An Empirical Framework and Verification Efficiency Matrix for Academic Librarians. Academic Research Journal of Science and Technology (ARJST). 2026;5(03):1-10. doi:10.63300/arjst0503062026.01

BibTeX
@article{Jaiswal2026,
  author = {Jaiswal, Karan and Kumar, Anurag},
  title = {Evaluating AI-Generated Citation Accuracy: An Empirical Framework and Verification Efficiency Matrix for Academic Librarians},
  journal = {Academic Research Journal of Science and Technology (ARJST)},
  year = {2026},
  volume = {5},
  number = {03},
  pages = {1--10},
  doi = {10.63300/arjst0503062026.01}
}
Kostenlos starten →