Efficient Prompting Methods for Large Language Models: A Survey
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929609850748928 |
|---|---|
| author | Chang, Kaiyan Xu, Songcheng Wang, Chenglong Luo, Yingfeng Liu, Xiaoqian Xiao, Tong Zhu, Jingbo |
| author_facet | Chang, Kaiyan Xu, Songcheng Wang, Chenglong Luo, Yingfeng Liu, Xiaoqian Xiao, Tong Zhu, Jingbo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01077 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Prompting Methods for Large Language Models: A Survey Chang, Kaiyan Xu, Songcheng Wang, Chenglong Luo, Yingfeng Liu, Xiaoqian Xiao, Tong Zhu, Jingbo Computation and Language 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. |
| title | Efficient Prompting Methods for Large Language Models: A Survey |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.01077 |