用可解释的优化准则提升提示词质量，让小模型也能高效生成好回答。
Rethinking Prompt Optimizers: From Prompt Merits to Optimization
- 基于通用提示质量标准，设计可解释的优化方法
- 在多类模型上实现更优表现，小模型性能提升显著
- 离线训练避免隐私泄露，适合实际部署
提示词优化（PO）为缺乏时间或专业知识的用户提供了一种提升回复质量的实用方法。现有方法通常依赖大模型自动生成提示词，但生成的指令密集型提示对轻量级推理模型负担过重，导致响应质量下降，且因隐式优化缺乏可解释性。本文从显式、可解释的设计角度重新思考提示词优化，首次识别出一组与模型无关的提示质量优势，并通过实证验证其对提示和响应质量的提升效果。随后提出MePO，一种基于这些优势构建的本地可部署优化器，其训练数据由轻量级模型生成的提示偏好数据集构成。MePO避免在线优化，降低隐私风险，通过学习清晰可解释的质量标准，在大模型和轻量级模型上均表现出良好泛化能力。实验表明，MePO在多种任务和模型类型中均取得更优结果，为实际部署提供了一种可扩展、鲁棒的解决方案。代码、模型与数据集详见 https://github.com/MidiyaZhu/MePO。
原文摘要 · Abstract (English)
Prompt optimization (PO) provides a practical way to improve response quality when users lack the time or expertise to manually craft effective prompts. Existing methods typically rely on LLMs' self-generation ability to optimize prompts. However, due to limited downward compatibility, the instruction-heavy prompts generated by advanced LLMs can overwhelm lightweight inference models and degrade response quality, while also lacking interpretability due to implicit optimization. In this work, we rethink prompt optimization through the lens of explicit and interpretable design. We first identify a set of model-agnostic prompt quality merits and empirically validate their effectiveness in enhancing prompt and response quality. We then introduce MePO, a merit-guided, locally deployable prompt optimizer trained on our merit-guided prompt preference dataset generated by a lightweight LLM. MePO avoids online optimization, reduces privacy concerns, and, by learning clear, interpretable merits, generalizes effectively to both large-scale and lightweight inference models. Experiments demonstrate that MePO achieves better results across diverse tasks and model types, offering a scalable and robust solution for real-world deployment. The code, model and dataset can be found in https://github.com/MidiyaZhu/MePO
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。