为复杂任务(如构建TripAdvisor聊天机器人)提示LLM需要人类明确表达定制化需求(如“以tl;dr开头”)。现有提示工程指令缺乏对需求表达的专注训练,而更强调可自动化的策略(如添加角色扮演和“逐步思考”技巧)。为弥补这一差距,我们引入需求导向的提示工程(ROPE),一种将人类注意力集中在生成清晰、完整需求的范式。我们通过评估和训练套件实现ROPE,提供有意识的练习与LLM生成反馈。在30名新手的随机对照实验中,ROPE显著优于传统提示工程训练(20% vs. 1%提升),这一差距自动提示优化无法弥补。此外,我们展示了输入需求质量与LLM输出之间的直接相关性。我们的工作为更多终端用户构建复杂LLM应用铺平了道路。
英文摘要:
Prompting LLMs for complex tasks (e.g., building a trip advisor chatbot) needs humans to clearly articulate customized requirements (e.g., "start the response with a tl;dr"). However, existing prompt engineering instructions often lack focused training on requirement articulation and instead tend to emphasize increasingly automatable strategies (e.g., tricks like adding role-plays and "think step-by-step"). To address the gap, we introduce Requirement-Oriented Prompt Engineering (ROPE), a paradigm that focuses human attention on generating clear, complete requirements during prompting. We implement ROPE through an assessment and training suite that provides deliberate practice with LLM-generated feedback. In a randomized controlled experiment with 30 novices, ROPE significantly outperforms conventional prompt engineering training (20% vs. 1% gains), a gap that automatic prompt optimization cannot close. Furthermore, we demonstrate a direct correlation between the quality of input requirements and LLM outputs. Our work paves the way to empower more end-users to build complex LLM applications.
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)
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)
Prompt Engineering for Healthcare: Methodologies and Applications
School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Computing, The University of Georgia(佐治亚大学计算学院);Department of Computer Science and Engineering, Lehigh University(利哈伊大学计算机科学与工程系);Department of Radiology, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院放射科);Department of Computer Science and Engineering, The University of Texas at Arlington(德克萨斯大学阿灵顿分校计算机科学与工程系);School of Biomedical Engineering, ShanghaiTech University(上海科技大学生物医学工程学院);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能医疗科技有限公司);Shanghai Clinical Research and Trial Center(上海临床研究与试验中心);Department of Electronic Engineering, City University of Hong Kong(香港城市大学电子工程系)
When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction
CSIRO’s Data61(CSIRO数据61实验室);Jiangxi Provincial Key Laboratory for High Performance Computing(江西省高性能计算重点实验室);State International Science & Technology Cooperation Base of Networked Supporting Software(网络化支持软件国际科技合作基地);Language Intelligence Research Center(语言智能研究中心);Jiangxi Normal University(江西师范大学);Institute of AI, Newcastle University, UK(人工智能研究院,新castle大学,英国);UGAiForge
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)
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))
Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study
Federal University of Bahia(巴伊亚联邦大学);State University of Feira de Santana(费拉德桑塔纳州立大学);Federal University of Sergipe(塞格皮联邦大学);Federal Institute of Ceara(塞阿拉联邦理工学院)
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室);Laboratory of Art and Archaeology Image (Zhejiang University), Ministry of Education(浙江大学艺术与考古图像实验室(教育部));Hong Kong University of Science and Technology(香港科技大学);Zhejiang University(浙江大学)
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)