ORPP：自优化角色扮演提示以增强语言模型能力
ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities
AI总结：
本文提出ORPP框架，通过将提示搜索空间限定在角色扮演场景并进行迭代优化与少样本迁移，以低计算开销生成高质量提示，在多数情况下超越现有提示优化方法并具备即插即用能力。
摘要：
高质量提示对于在复杂任务上激发大型语言模型（LLMs）的出色表现至关重要。现有研究已经探索了模型驱动的提示优化策略。然而，这些方法通常面临计算开销高或需要模型自身具备较强优化能力的问题，从而限制了它们的广泛适用性。为应对这些挑战，我们提出了ORPP（Optimized Role-Playing Prompt，优化角色扮演提示），这是一个通过优化和生成角色扮演提示来提升模型性能的框架。ORPP的核心思想是将提示搜索空间限制在角色扮演场景中，从而通过精心设计的高质量角色扮演提示充分激活模型的内在能力。具体而言，ORPP首先在一小部分训练样本上进行迭代优化，以生成高质量的角色扮演提示。然后，利用模型的少样本学习能力，将优化经验迁移到其余样本上，从而高效地生成合适的提示。我们的实验结果表明，ORPP不仅在性能上与现有主流提示优化方法相当，而且在大多数情况下超越了它们。值得注意的是，ORPP展现出优越的“即插即用”能力。在大多数情况下，它可以与各种其他提示方法集成，并进一步提升它们的有效性。
英文摘要：
High-quality prompts are crucial for eliciting outstanding performance from large language models (LLMs) on complex tasks. Existing research has explored model-driven strategies for prompt optimization. However, these methods often suffer from high computational overhead or require strong optimization capabilities from the model itself, which limits their broad applicability.To address these challenges, we propose ORPP (Optimized Role-Playing Prompt),a framework that enhances model performance by optimizing and generating role-playing prompts. The core idea of ORPP is to confine the prompt search space to role-playing scenarios, thereby fully activating the model's intrinsic capabilities through carefully crafted, high-quality role-playing prompts. Specifically, ORPP first performs iterative optimization on a small subset of training samples to generate high-quality role-playing prompts. Then, leveraging the model's few-shot learning capability, it transfers the optimization experience to efficiently generate suitable prompts for the remaining samples.Our experimental results show that ORPP not only matches but in most cases surpasses existing mainstream prompt optimization methods in terms of performance. Notably, ORPP demonstrates superior "plug-and-play" capability. In most cases, it can be integrated with various other prompt methods and further enhance their effectiveness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
