A Systematic Survey of Automatic Prompt Optimization Techniques
This is an incremental survey that addresses the problem of making prompt engineering more accessible for end users in NLP by organizing and analyzing automated optimization methods.
This paper tackles the challenge of prompt engineering for large language models by conducting a systematic survey of automatic prompt optimization techniques, providing a formal definition, a unifying framework, and a categorization of existing works to summarize progress and identify remaining challenges.
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.