Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation.

Journal: Journal of biomedical informatics
Published Date:

Abstract

OBJECTIVE: The paper introduces a framework for the evaluation of the encoding of factual scientific knowledge, designed to streamline the manual evaluation process typically conducted by domain experts. Inferring over and extracting information from Large Language Models (LLMs) trained on a large corpus of scientific literature can potentially define a step change in biomedical discovery, reducing the barriers for accessing and integrating existing medical evidence. This work explores the potential of LLMs for dialoguing with biomedical background knowledge, using the context of antibiotic discovery.

Authors

  • Magdalena Wysocka
    Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester, Oxford Rd, Manchester, M13 9 PL, UK. magdalena.wysocka@manchester.ac.uk.
  • Oskar Wysocki
    Cancer Research UK Manchester Institute, University of Manchester, Oxford Rd, Manchester M13 9PL, United Kingdom; Idiap Research Institute, National University of Sciences, Rue Marconi 19, CH - 1920 Martigny, Switzerland.
  • Maxime Delmas
    Idiap Research Institute, Martigny, Switzerland.
  • Vincent Mutel
    Inflamalps SA, Monthey, Switzerland.
  • Andre Freitas
    Department of Computer Science, University of Manchester, Manchester, UK.