AMPO: Automatic Multi-Branched Prompt Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909345499840512 |
|---|---|
| author | Yang, Sheng Wu, Yurong Gao, Yan Zhou, Zineng Zhu, Bin Benjamin Sun, Xiaodi Lou, Jian-Guang Ding, Zhiming Hu, Anbang Fang, Yuan Li, Yunsong Chen, Junyan Yang, Linjun |
| author_facet | Yang, Sheng Wu, Yurong Gao, Yan Zhou, Zineng Zhu, Bin Benjamin Sun, Xiaodi Lou, Jian-Guang Ding, Zhiming Hu, Anbang Fang, Yuan Li, Yunsong Chen, Junyan Yang, Linjun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08696 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AMPO: Automatic Multi-Branched Prompt Optimization Yang, Sheng Wu, Yurong Gao, Yan Zhou, Zineng Zhu, Bin Benjamin Sun, Xiaodi Lou, Jian-Guang Ding, Zhiming Hu, Anbang Fang, Yuan Li, Yunsong Chen, Junyan Yang, Linjun Computation and Language 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. |
| title | AMPO: Automatic Multi-Branched Prompt Optimization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.08696 |