The field of prompt engineering is becoming an essential phenomenon in artificial intelligence. It is altering how data scientists interact with large language models (LLMs) for analytics applications. This research paper shares empirical results from different studies on prompt engineering with regards to its methodology, effectiveness, and applications. Through case studies in healthcare, materials science, financial services, and business intelligence, we demonstrate how the use of structured prompting techniques can improve performance on a range of tasks by between 6% and more than 30%. The effectiveness of prompts relies on their complexity, according to our findings. Further, model architecture and optimisation strategy also depend on these factors as well. We also found promise in advanced frameworks such as chain-of-thought reasoning and automatic optimisers. The proof indicates that prompt engineering allows access to strong AI localisation. Nonetheless, there is plenty of information regarding standardisation, interpretability and the ethical use of AI.

翻译：提示工程领域正成为人工智能中一个至关重要的现象。它正在改变数据科学家为分析应用与大型语言模型（LLM）交互的方式。本研究论文分享了关于提示工程方法、有效性及应用的不同实证研究结果。通过医疗保健、材料科学、金融服务和商业智能等领域的案例研究，我们证明了使用结构化提示技术可将一系列任务的性能提升6%至30%以上。根据我们的发现，提示的有效性取决于其复杂性。此外，模型架构和优化策略也依赖于这些因素。我们还发现诸如思维链推理和自动优化器等先进框架具有应用前景。证据表明，提示工程能够实现强大的AI本地化。然而，在标准化、可解释性及AI伦理使用方面仍存在大量待探索的信息。