系统梳理自动提示优化技术，帮用户轻松提升大模型表现。
A Systematic Survey of Automatic Prompt Optimization Techniques
- 提出五部分统一框架，分类整理自动提示优化方法
- 归纳现有技术进展，指出现有挑战与研究空白
- 适合对大模型提示工程感兴趣的科研人员与开发者
自大语言模型（LLMs）问世以来，提示工程在各类自然语言处理任务中成为关键步骤。然而，随着模型、任务及最佳实践的快速演进，提示工程对终端用户仍构成障碍。为此，自动提示优化（APO）技术应运而生，通过自动化手段提升大模型在各类任务上的表现。本文系统综述该领域的最新进展与未解挑战，给出APO的正式定义，构建五部分统一框架，并据此严谨分类所有相关工作。希望本框架能推动后续研究发展。
原文摘要 · Abstract (English)
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated best practices. To mitigate this, Automatic Prompt Optimization (APO) techniques have recently emerged that use various automated techniques to help improve the performance of LLMs on various tasks. In this paper, we present a comprehensive survey summarizing the current progress and remaining challenges in this field. We provide a formal definition of APO, a 5-part unifying framework, and then proceed to rigorously categorize all relevant works based on their salient features therein. We hope to spur further research guided by our framework.
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。