Efficient Prompting Methods for Large Language Models: A Survey
This is an incremental survey that summarizes existing methods to improve efficiency in prompting for NLP tasks, targeting researchers and practitioners using large language models.
The paper surveys efficient prompting methods for large language models, addressing the resource consumption issues of manual prompt engineering and computational burdens, and discusses automatic prompt engineering and prompt compression techniques.
Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external prompts, which inevitably brings extra human efforts and computational burdens for practical applications. As an effective solution to mitigate resource consumption, Efficient Prompting Methods have attracted a wide range of attention. We provide mathematical expressions at a high level to deeply discuss Automatic Prompt Engineering for different prompt components and Prompt Compression in continuous and discrete spaces. Finally, we highlight promising future directions to inspire researchers interested in this field.