Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance model efficacy without modifying the core model parameters. Rather than updating the model parameters, prompts allow seamless integration of pre-trained models into downstream tasks by eliciting desired model behaviors solely based on the given prompt. Prompts can be natural language instructions that provide context to guide the model or learned vector representations that activate relevant knowledge. This burgeoning field has enabled success across various applications, from question-answering to commonsense reasoning. However, there remains a lack of systematic organization and understanding of the diverse prompt engineering methods and techniques. This survey paper addresses the gap by providing a structured overview of recent advancements in prompt engineering, categorized by application area. For each prompting approach, we provide a summary detailing the prompting methodology, its applications, the models involved, and the datasets utilized. We also delve into the strengths and limitations of each approach and include a taxonomy diagram and table summarizing datasets, models, and critical points of each prompting technique. This systematic analysis enables a better understanding of this rapidly developing field and facilitates future research by illuminating open challenges and opportunities for prompt engineering.
Effects of a Prompt Engineering Intervention on Undergraduate Students' AI Self-Efficacy, AI Knowledge and Prompt Engineering Ability: A Mixed Methods Study
Precious Blood Secondary School（宝血女子中学）；The University of Hong Kong（香港大学）
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
University of Maryland（马里兰大学）；Learn Prompting；OpenAI；Stanford（斯坦福大学）；Microsoft（微软公司）；Vanderbilt（范德堡大学）；Princeton（普林斯顿大学）；Texas State University（德克萨斯州立大学）；Icahn School of Medicine（伊坎医学院）；ASST Brianza（布里安扎综合医院）；Mount Sinai Beth Israel（西奈山 Beth Israel 医院）；Instituto de Telecomunicações（电信研究所）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学清华大学深圳国际研究生院）；School of Automation, Wuhan University of Technology（武汉理工大学自动化学院）
Unleashing the potential of prompt engineering for large language models
Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science（interdisciplinary Research and Application for Data Science省重点实验室）；BNU-HKBU United International College（北京师范大学-香港浸会大学联合国际学院）；Research Center for Mathematics, Beijing Normal University（北京师范大学数学研究中心）
Characterizing Fitness Landscape Structures in Prompt Engineering
Department of Data Analytics, Dalarna University（数据分析系，达拉那大学）；BEACON Institute for the Study of Evolution in Action, Michigan State University（进化行为研究所，密歇根州立大学）
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
Shenzhen Technology University（深圳技术大学）；The Hong Kong Polytechnic University（香港理工大学）；Zhejiang Lab（之江实验室）；The Chinese University of Hong Kong（香港中文大学）；HKUST (Guangzhou)（香港科技大学（广州））
Few-Shot Learning for Mental Disorder Detection: A Continuous Multi-Prompt Engineering Approach with Medical Knowledge Injection
Hefei University of Technology（合肥工业大学）；Iowa State University（爱荷华州立大学）；University of Delaware（特拉华大学）；University of Rhode Island（罗德岛大学）；University of Arizona（亚利桑那大学）
Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices
Geneva University Hospitals（日内瓦大学医院）；University of Geneva（日内瓦大学）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；Sorbonne Université（索邦大学）；INSERM（法国国家健康与医学研究院）；Université Sorbonne Paris-Nord（索邦巴黎北大学）
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
Brigham Young University（杨百翰大学）
预先训练的语言模型从它们所训练的大量语料库中获得大量的语言和事实知识，并且提示工程试图将这些模型与特定任务相匹配。不幸的是，现有的提示工程方法需要大量的标记数据，访问模型参数，或两者兼而有之。本文介绍了一种新的选择提示模板\textit{without labeled examples}和\textit{without direct access to the model}的方法。具体来说，在一组候选模板，我们选择的模板，最大化的互信息之间的输入和相应的模型输出。在8个数据集，代表7个不同的NLP任务，我们表明，当一个模板具有高互信息，它也有高精度的任务。在最大的模型上，使用我们的方法选择提示可以获得从平均提示准确度到最佳提示准确度的90%，并且不需要真值标签。
