EMNLP 2024main3 citations

AMPO: Automatic Multi-Branched Prompt Optimization

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Benjamin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding

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.

BibTeX
@inproceedings{yang-etal-2024-ampo,
    title = "{AMPO}: Automatic Multi-Branched Prompt Optimization",
    author = "Yang, Sheng  and
      Wu, Yurong  and
      Gao, Yan  and
      Zhou, Zineng  and
      Zhu, Bin Benjamin  and
      Sun, Xiaodi  and
      Lou, Jian-Guang  and
      Ding, Zhiming  and
      Hu, Anbang  and
      Fang, Yuan  and
      Li, Yunsong  and
      Chen, Junyan  and
      Yang, Linjun",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.1130/",
    doi = "10.18653/v1/2024.emnlp-main.1130",
    pages = "20267--20279"
}
AMPO: Automatic Multi-Branched Prompt Optimization · EMNLP 2024