P3: Prompts Promote Prompting
This addresses the problem of interdependent prompt optimization for LLM users, offering a holistic strategy that is incremental over prior unilateral methods.
The paper tackles the suboptimal performance from unilateral optimization of system or user prompts in LLMs by introducing P3, a self-improvement framework that concurrently optimizes both components, achieving superior performance on general and reasoning tasks.
Current large language model (LLM) applications often employ multi-component prompts, comprising both system and user prompts, to guide model behaviors. While recent advancements have demonstrated the efficacy of automatically optimizing either the system or user prompt to boost performance, such unilateral approaches often yield suboptimal outcomes due to the interdependent nature of these components. In this work, we introduce P3, a novel self-improvement framework that concurrently optimizes both system and user prompts through an iterative process. The offline optimized prompts are further leveraged to promote online prompting by performing query-dependent prompt optimization. Extensive experiments on general tasks (e.g., Arena-hard and Alpaca-eval) and reasoning tasks (e.g., GSM8K and GPQA) demonstrate that P3 achieves superior performance in the realm of automatic prompt optimization. Our results highlight the effectiveness of a holistic optimization strategy in enhancing LLM performance across diverse domains.