Fast information and slow evidence in the large language models era.

Abstract

LLMs accelerate medical information work, but speed of synthesis does not justify reliance. As T.S. Eliot asked, "Where is the knowledge we have lost in information?" Using a data-information-evidence-practice hierarchy, LLM outputs enter clinical setting as information and become evidence only through appraisal, validation, and contextual judgement. We highlight how LLMs can support evidence infrastructures, clarify evidence boundaries, and reshape clinical expertise to strengthen rather than replace evidence-based medicine.