教普通人如何清晰表达需求，让大模型更好理解任务。
What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use
- 聚焦需求表述训练，而非堆砌提示技巧。
- 新手使用新方法后任务完成率提升20%，远超传统方法的1%。
- 需求质量直接决定输出效果，适合想用大模型做应用的普通用户。
在复杂任务（如构建旅行助手聊天机器人）中，需人类明确表达定制化需求（如“回复开头加tl;dr”）。但现有提示工程指导常忽略需求表述训练，转而强调可自动化策略（如角色扮演、“逐步思考”等技巧）。为此，我们提出需求导向提示工程（ROPE），将人类注意力集中于生成清晰、完整的需求。通过评估与训练套件提供基于大模型反馈的刻意练习，在30名初学者的随机对照实验中，ROPE显著优于传统训练（20%对比1%提升），且自动提示优化无法弥补这一差距。进一步证明输入需求质量与大模型输出之间存在直接关联。本研究为更多终端用户构建复杂大模型应用铺平道路。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。