Personas Shift Clinical Action Thresholds in Large Language Models
Decision-style system prompts reliably change clinical action thresholds in LLMs under fixed evidence. Prompting is a policy-setting layer, not just a communication layer, and should be treated as a first-class deployment configuration.
Authors
- Mahmud Omar
- Eyal Klang (ORCID: https://orcid.org/0000-0002-4567-3108)
- Alon Gorenshtein (ORCID: https://orcid.org/0009-0000-7542-8608)
- Girish Nadkarni
Institutions
- Mount Sinai Health System (US)
- Mount Sinai Medical Center (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-01-02
- DOI
- https://doi.org/10.64898/2026.01.01.26343302
- Primary Topic
- Persona Design and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Georgia Clinical and Translational Science Alliance
- National Institutes of Health
- National Center for Advancing Translational Sciences