Evaluating the Efficacy of Perplexity Scores in Distinguishing AI-Generated and Human-Written Abstracts.

Journal: Academic radiology
PMID: 39915182

Abstract

RATIONALE AND OBJECTIVES: We aimed to evaluate the efficacy of perplexity scores in distinguishing between human-written and AI-generated radiology abstracts and to assess the relative performance of available AI detection tools in detecting AI-generated content.

Authors

  • Alperen Elek
    Ege University Faculty of Medicine, Izmir, Turkey (A.E.). Electronic address: alperenelek13@gmail.com.
  • Hatice Sude Yildiz
    Adıyaman University Faculty of Medicine, Adıyaman, Turkey (H.S.Y.).
  • Benan Akca
    Marmara University, Electrical-Electronics Engineering Department, Istanbul, Turkey (B.A.).
  • Nisa Cem Oren
    Advanced Midwest Radiology Illinois, Oak Brook, Illinois (N.C.O.).
  • Batuhan Gundogdu
    University of Chicago, Department of Radiology, Chicago, Illinois (B.G.).

Keywords

External Resources

Popular Topics
Recent Journals