提出深度学习启发的提示优化框架，提升自动化提示设计的鲁棒性与效率。
DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective
- 借鉴深度学习思想，设计七种新型提示优化方法。
- 在多个任务上实现更优的泛化性能与计算效率。
- 适合对提示工程和模型效率感兴趣的开发者与研究者。
大型语言模型在众多任务中取得显著成功，主要依赖于精心设计的提示。然而，提示的构建与选择通常需要大量人工干预，严重制约其可扩展性。为缓解此问题，近期研究探索了自动化提示优化这一有前景的方向。尽管已有进展，现有方法在鲁棒性、效率和泛化能力方面仍面临关键挑战。为此，我们首先通过实证分析识别出当前基于反思的提示优化范式的局限性。基于这些洞察，我们提出七种受传统深度学习范式启发的提示优化方法（DLPO），并将其无缝融入基于文本的梯度优化流程。通过一系列实验，我们逐步解决了上述挑战，并验证了方法的有效性。本研究不仅为未来研究提供重要指引，也深化了对提示优化中核心问题与潜在解决方案的理解。代码已开源：https://github.com/sfasfaffa/DLPO。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have achieved remarkable success across diverse tasks, largely driven by well-designed prompts. However, crafting and selecting such prompts often requires considerable human effort, significantly limiting its scalability. To mitigate this, recent studies have explored automated prompt optimization as a promising solution. Despite these efforts, existing methods still face critical challenges in robustness, efficiency, and generalization. To systematically address these challenges, we first conduct an empirical analysis to identify the limitations of current reflection-based prompt optimization paradigm. Building on these insights, we propose 7 innovative approaches inspired by traditional deep learning paradigms for prompt optimization (DLPO), seamlessly integrating these concepts into text-based gradient optimization. Through these advancements, we progressively tackle the aforementioned challenges and validate our methods through extensive experimentation. We hope our study not only provides valuable guidance for future research but also offers a comprehensive understanding of the challenges and potential solutions in prompt optimization. Our code is available at https://github.com/sfasfaffa/DLPO.
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。