Results Given the critical role of prompt optimization in enhancing LLM performance, we first evaluated whether designing a specific prompt structure would optimize the accuracy of a representative LLM (Mistral Nemo 12B) in accurately retrieving FDA-approved biomarker-based (“precision”) oncology therapies.25 We tested four distinct prompt strategies (see STAR MethodsTable 1). All evaluated queries were formulated using the structured data from MOAlmanac v2024-04-11 (Tables S1 and S2).
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Get in touch with Dan Y.
Contact Dan Y., search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack