Performance and Reproducibility of Large Language Models in Named Entity Recognition: Considerations for the Use in Controlled Environments.

Journal: Drug safety
Published Date:

Abstract

INTRODUCTION: Recent artificial intelligence (AI) advances can generate human-like responses to a wide range of queries, making them a useful tool for healthcare applications. Therefore, the potential use of large language models (LLMs) in controlled environments regarding efficacy, reproducibility, and operability will be of paramount interest.

Authors

  • Jürgen Dietrich
    Bayer AG, Pharmaceuticals, Pharmacovigilance, Innovation and Digitalization, Berlin, Germany.
  • André Hollstein
    Pharmaceuticals, Medical Affairs and Pharmacovigilance, Data Science and Insights, Bayer AG, Müllerstr. 178, 13353, Berlin, Germany.