English

Dual-Phase Accelerated Prompt Optimization

Computation and Language 2024-10-03 v2

Abstract

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-quality initial prompts by adopting a well-designed meta-instruction to delve into task-specific information, and iteratively optimize the prompts at the sentence level, leveraging previous tuning experience to expand prompt candidates and accept effective ones. Extensive experiments on eight datasets demonstrate the effectiveness of our proposed method, achieving a consistent accuracy gain over baselines with less than five optimization steps.

Keywords

Cite

@article{arxiv.2406.13443,
  title  = {Dual-Phase Accelerated Prompt Optimization},
  author = {Muchen Yang and Moxin Li and Yongle Li and Zijun Chen and Chongming Gao and Junqi Zhang and Yangyang Li and Fuli Feng},
  journal= {arXiv preprint arXiv:2406.13443},
  year   = {2024}
}

Comments

EMNLP 2024 Findings

R2 v1 2026-06-28T17:11:58.582Z