EUVIMEDEUVIMED entdecken
Crossref

Generative AI in Peer Review: An Evaluation of Capabilities, Limitations, and Responsible Implementation Strategies

Zhongshi Wang, Mengyue Gong

Journal of Scholarly Communication · 2026

DOI: 10.62160/jsc44 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Scholarly Communication, 2026. Verfasst von Zhongshi Wang und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative artificial intelligence (GenAI) has been increasingly integrated in academic publishing process. This study aims to access the performance of GenAI in peer review using multi-disciplinary manuscript samples. Five GenAI models underwent peer review tests, systematically evaluated for completeness, accuracy, and rationality of responses using combined manual scoring and statistical analysis. Findings indicated high accuracy in summarizing manuscript content and identifying suitable journals. However, GenAI models exhibited significant limitations in identifying scientific errors and evaluating paper innovation. The results demonstrate clear competency boundaries for GenAI within the peer review, particularly concerning tasks requiring nuanced professional judgment. This study clarifies the potential application scope of GenAI in peer review and provides a basis for its responsible future implementation.

Zitieren

APA

Wang, Z., & Gong, M. (2026). Generative AI in Peer Review: An Evaluation of Capabilities, Limitations, and Responsible Implementation Strategies. Journal of Scholarly Communication. https://doi.org/10.62160/jsc44

Vancouver

Wang Z, Gong M. Generative AI in Peer Review: An Evaluation of Capabilities, Limitations, and Responsible Implementation Strategies. Journal of Scholarly Communication. 2026. doi:10.62160/jsc44

BibTeX
@article{Wang2026,
  author = {Wang, Zhongshi and Gong, Mengyue},
  title = {Generative AI in Peer Review: An Evaluation of Capabilities, Limitations, and Responsible Implementation Strategies},
  journal = {Journal of Scholarly Communication},
  year = {2026},
  doi = {10.62160/jsc44}
}
Kostenlos starten →