提升大模型提示词进化搜索的效率与质量
A Toolbox for Improving Evolutionary Prompt Search
- 将进化过程拆分为独立步骤，增强控制性
- 引入LLM裁判验证进化结果，提高可靠性
- 融合人类反馈优化算子，适合提示工程研究者
进化式提示优化在改进大模型提示词方面已证明有效，但现有方法缺乏稳健的算子和高效的评估机制。本文提出若干关键改进：1）将进化过程分解为独立步骤，提升可控性；2）引入基于LLM的裁判模型验证进化结果；3）结合人类反馈优化进化算子；4）开发更高效的评估策略，在保持性能的同时降低计算开销。所提方法显著提升了优化质量和效率。代码已开源，支持新任务上的提示优化，并推动该领域进一步研究。
原文摘要 · Abstract (English)
Evolutionary prompt optimization has demonstrated effectiveness in refining prompts for LLMs. However, existing approaches lack robust operators and efficient evaluation mechanisms. In this work, we propose several key improvements to evolutionary prompt optimization that can partially generalize to prompt optimization in general: 1) decomposing evolution into distinct steps to enhance the evolution and its control, 2) introducing an LLM-based judge to verify the evolutions, 3) integrating human feedback to refine the evolutionary operator, and 4) developing more efficient evaluation strategies that maintain performance while reducing computational overhead. Our approach improves both optimization quality and efficiency. We release our code, enabling prompt optimization on new tasks and facilitating further research in this area.
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。