自动为任务匹配最佳提示策略，让外行也能高效使用大模型。
Automatic Prompt Generation via Adaptive Selection of Prompting Techniques
- 根据任务语义聚类，动态选择适配的提示技术。
- 在23个高难度任务上超越标准提示和现有工具。
- 无需模板，适合无提示工程经验的用户。
提示工程对大语言模型生成可靠有效输出至关重要，但其设计需掌握特定提示技巧并理解目标任务。为此，我们提出一种新方法：基于用户提供的抽象任务描述，自适应选择适配的提示技术，并自动生成高质量提示，无需依赖预设模板或框架。该方法构建一个知识库，将语义相似的任务聚类与对应提示技术关联起来。当输入任务描述时，系统将其分配至最相关任务聚类，并从知识库中动态整合技术生成提示。在23个来自BIG-Bench Extra Hard（BBEH）的高难度任务上的实验评估显示，该方法在算术均值与调和均值评分上均优于标准提示和现有自动提示生成工具。本研究为简化和标准化提示创建奠定了基础，使非专家也能有效利用大语言模型。
原文摘要 · Abstract (English)
Prompt engineering is crucial for achieving reliable and effective outputs from large language models (LLMs), but its design requires specialized knowledge of prompting techniques and a deep understanding of target tasks. To address this challenge, we propose a novel method that adaptively selects task-appropriate prompting techniques based on users' abstract task descriptions and automatically generates high-quality prompts without relying on pre-existing templates or frameworks. The proposed method constructs a knowledge base that associates task clusters, characterized by semantic similarity across diverse tasks, with their corresponding prompting techniques. When users input task descriptions, the system assigns them to the most relevant task cluster and dynamically generates prompts by integrating techniques drawn from the knowledge base. An experimental evaluation of the proposed method on 23 tasks from BIG-Bench Extra Hard (BBEH) demonstrates superior performance compared with standard prompts and existing automatic prompt-generation tools, as measured by both arithmetic and harmonic mean scores. This research establishes a foundation for streamlining and standardizing prompt creation, enabling non-experts to effectively leverage LLMs.
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。