{"ID":2878412,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17703","arxiv_id":"2508.17703","title":"EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning","abstract":"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.","short_abstract":"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 enh...","url_abs":"https://arxiv.org/abs/2508.17703","url_pdf":"https://arxiv.org/pdf/2508.17703v1","authors":"[\"Yinda Chen\",\"Yangfan He\",\"Jing Yang\",\"Dapeng Zhang\",\"Zhenlong Yuan\",\"Muhammad Attique Khan\",\"Jamel Baili\",\"Por Lip Yee\"]","published":"2025-08-25T06:23:17Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}