Prompt engineering significantly influences the reliability and clinical utility of Large Language Models (LLMs) in medical applications. Current optimization approaches inadequately address domain-specific medical knowledge and safety requirements. This paper introduces EMPOWER, a novel evolutionary framework that enhances medical prompt quality through specialized representation learning, multi-dimensional evaluation, and structure-preserving algorithms. Our methodology incorporates: (1) a medical terminology attention mechanism, (2) a comprehensive assessment architecture evaluating clarity, specificity, clinical relevance, and factual accuracy, (3) a component-level evolutionary algorithm preserving clinical reasoning integrity, and (4) a semantic verification module ensuring adherence to medical knowledge. Evaluation across diagnostic, therapeutic, and educational tasks demonstrates significant improvements: 24.7% reduction in factually incorrect content, 19.6% enhancement in domain specificity, and 15.3% higher clinician preference in blinded evaluations. The framework addresses critical challenges in developing clinically appropriate prompts, facilitating more responsible integration of LLMs into healthcare settings.
@article{arxiv.2508.17703,
title = {EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning},
author = {Yinda Chen and Yangfan He and Jing Yang and Dapeng Zhang and Zhenlong Yuan and Muhammad Attique Khan and Jamel Baili and Por Lip Yee},
journal= {arXiv preprint arXiv:2508.17703},
year = {2025}
}