AMPO: Automatic Multi-Branched Prompt Optimization

TL;DR

AMPO introduces an automatic method to optimize multi-branched prompts for large language models, effectively handling diverse patterns in complex tasks through iterative feedback and minimal search strategies.

Contribution

This paper presents a novel multi-branched prompt optimization approach that outperforms existing single-flow methods by using failure feedback and structured prompt design.

Findings

AMPO achieves the best results across five tasks.

It demonstrates significant optimization efficiency.

It effectively handles multiple patterns in complex tasks.

Abstract

Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize the prompts, achieving satisfying results. However, existing automatic prompt optimization techniques are only limited to producing single flow instructions, struggling with handling diverse patterns. In this paper, we present AMPO, an automatic prompt optimization method that can iteratively develop a multi-branched prompt using failure cases as feedback. Our goal is to explore a novel way of structuring prompts with multi-branches to better handle multiple patterns in complex tasks, for which we introduce three modules: Pattern Recognition, Branch Adjustment, and Branch Pruning. In experiments across five tasks, AMPO consistently achieves the best results. Additionally, our approach demonstrates significant optimization efficiency due to our adoption of a minimal search strategy.