StraGo: Harnessing Strategic Guidance for 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_ | 1866914970059407360 |
|---|---|
| author | Wu, Yurong Gao, Yan Zhu, Bin Benjamin Zhou, Zineng Sun, Xiaodi Yang, Sheng Lou, Jian-Guang Ding, Zhiming Yang, Linjun |
| author_facet | Wu, Yurong Gao, Yan Zhu, Bin Benjamin Zhou, Zineng Sun, Xiaodi Yang, Sheng Lou, Jian-Guang Ding, Zhiming Yang, Linjun |
| contents | Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where newly generated prompts can adversely impact previously successful cases while addressing failures. Furthermore, these methods tend to rely heavily on LLMs' intrinsic capabilities for prompt optimization tasks. In this paper, we introduce StraGo (Strategic-Guided Optimization), a novel approach designed to mitigate prompt drifting by leveraging insights from both successful and failed cases to identify critical factors for achieving optimization objectives. StraGo employs a how-to-do methodology, integrating in-context learning to formulate specific, actionable strategies that provide detailed, step-by-step guidance for prompt optimization. Extensive experiments conducted across a range of tasks, including reasoning, natural language understanding, domain-specific knowledge, and industrial applications, demonstrate StraGo's superior performance. It establishes a new state-of-the-art in prompt optimization, showcasing its ability to deliver stable and effective prompt improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08601 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StraGo: Harnessing Strategic Guidance for Prompt Optimization Wu, Yurong Gao, Yan Zhu, Bin Benjamin Zhou, Zineng Sun, Xiaodi Yang, Sheng Lou, Jian-Guang Ding, Zhiming Yang, Linjun Computation and Language Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where newly generated prompts can adversely impact previously successful cases while addressing failures. Furthermore, these methods tend to rely heavily on LLMs' intrinsic capabilities for prompt optimization tasks. In this paper, we introduce StraGo (Strategic-Guided Optimization), a novel approach designed to mitigate prompt drifting by leveraging insights from both successful and failed cases to identify critical factors for achieving optimization objectives. StraGo employs a how-to-do methodology, integrating in-context learning to formulate specific, actionable strategies that provide detailed, step-by-step guidance for prompt optimization. Extensive experiments conducted across a range of tasks, including reasoning, natural language understanding, domain-specific knowledge, and industrial applications, demonstrate StraGo's superior performance. It establishes a new state-of-the-art in prompt optimization, showcasing its ability to deliver stable and effective prompt improvements. |
| title | StraGo: Harnessing Strategic Guidance for Prompt Optimization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.08601 |