Designing Large Language Models That Refuse Unsafe Medication Questions Well
Archives of Pharmacy Practice · 2026 · 17 (1) · 77-84
DOI: 10.51847/msrqginb22 ↗Kurz gefasst
Fachartikel in der Zeitschrift Archives of Pharmacy Practice, 2026. Verfasst von Gabriel Costa und 3 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben.
Abstract (Originalsprache)
Large language models can produce fluent medication information while remaining vulnerable to factual error, missing context, unsafe personalization, adversarial manipulation, and misleading confidence. Refusal is therefore not merely a conversational limitation; when appropriately designed, it may function as a medication-safety control. This article develops a proposed Pharmacy Refusal-Safety Framework for determining when a model should answer, qualify, redirect, or refuse a medication questi
Zitieren
APA
Costa, G., Ribeiro, L., Alves, R., & Lopes, M. (2026). Designing Large Language Models That Refuse Unsafe Medication Questions Well. Archives of Pharmacy Practice, 17(1), 77-84. https://doi.org/10.51847/msrqginb22
Vancouver
Costa G, Ribeiro L, Alves R, Lopes M. Designing Large Language Models That Refuse Unsafe Medication Questions Well. Archives of Pharmacy Practice. 2026;17(1):77-84. doi:10.51847/msrqginb22
BibTeX
@article{Costa2026,
author = {Costa, Gabriel and Ribeiro, Lucas and Alves, Ricardo and Lopes, Mariana},
title = {Designing Large Language Models That Refuse Unsafe Medication Questions Well},
journal = {Archives of Pharmacy Practice},
year = {2026},
volume = {17},
number = {1},
pages = {77--84},
doi = {10.51847/msrqginb22}
}
EUVIMED