| Title: |
A Systematic Survey of Automatic Prompt Optimization Techniques |
| Authors: |
Ramnath, Kiran; Zhou, Kang; Guan, Sheng; Mishra, Soumya Smruti; Qi, Xuan; Shen, Zhengyuan; Wang, Shuai; Woo, Sangmin; Jeoung, Sullam; Wang, Yawei; Wang, Haozhu; Ding, Han; Lu, Yuzhe; Xu, Zhichao; Zhou, Yun; Srinivasan, Balasubramaniam; Yan, Qiaojing; Chen, Yueyan; Ding, Haibo; Xu, Panpan; Cheong, Lin Lee |
| Publication Year: |
2025 |
| Collection: |
ArXiv.org (Cornell University Library) |
| Subject Terms: |
Computation and Language; Artificial Intelligence |
| Description: |
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated best practices. To mitigate this, Automatic Prompt Optimization (APO) techniques have recently emerged that use various automated techniques to help improve the performance of LLMs on various tasks. In this paper, we present a comprehensive survey summarizing the current progress and remaining challenges in this field. We provide a formal definition of APO, a 5-part unifying framework, and then proceed to rigorously categorize all relevant works based on their salient features therein. We hope to spur further research guided by our framework. ; 8 main pages, 31 total pages, 1 figure |
| Document Type: |
text |
| Language: |
unknown |
| Relation: |
http://arxiv.org/abs/2502.16923 |
| DOI: |
10.18653/v1/2025.emnlp-main.1681 |
| Availability: |
http://arxiv.org/abs/2502.16923; https://doi.org/10.18653/v1/2025.emnlp-main.1681 |
| Accession Number: |
edsbas.B6A92747 |
| Database: |
BASE |