Tripathi Satvik, Alkhulaifat Dana, Lyo Shawn, Sukumaran Rithvik, Li Bolin, Acharya Vedant, McBeth Rafe, Cook Tessa S
Department of Radiology, Perelman School of Medicine at University of Pennsylvania, Philadelphia, Pennsylvania; Department of Radiation Oncology, Perelman School of Medicine at University of Pennsylvania, Philadelphia, Pennsylvania.
Department of Radiology, Perelman School of Medicine at University of Pennsylvania, Philadelphia, Pennsylvania; Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania.
J Am Coll Radiol. 2025 Jul;22(7):841-847. doi: 10.1016/j.jacr.2025.02.051.
Large language models (LLMs) are reshaping radiology through their advanced capabilities in tasks such as medical report generation and clinical decision support. However, their effectiveness is heavily influenced by prompt engineering-the design of input prompts that guide the model's responses. This review aims to illustrate how different prompt engineering techniques, including zero-shot, one-shot, few-shot, chain of thought, and tree of thought, affect LLM performance in a radiology context. In addition, we explore the impact of prompt complexity and temperature settings on the relevance and accuracy of model outputs. This article highlights the importance of precise and iterative prompt design to enhance LLM reliability in radiology, emphasizing the need for methodological rigor and transparency to drive progress and ensure ethical use in health care.
大语言模型（LLMs）正通过其在医学报告生成和临床决策支持等任务中的先进能力重塑放射学。然而，它们的有效性在很大程度上受到提示工程的影响，提示工程是指引导模型响应的输入提示的设计。本综述旨在说明不同的提示工程技术，包括零样本、一样本、少样本、思维链和思维树，如何在放射学背景下影响大语言模型的性能。此外，我们还探讨了提示复杂性和温度设置对模型输出的相关性和准确性的影响。本文强调了精确且迭代的提示设计对于提高放射学中大语言模型可靠性的重要性，强调了方法的严谨性和透明度对于推动进展以及确保在医疗保健中的道德使用的必要性。
