MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization

Yuyan Chen, Zhihao Wen, Ge Fan, Zhengyu Chen, Wei Wu, Dayiheng Liu, Zhixu Li, Bang Liu, Yanghua Xiao


Abstract
Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to specific tasks, rather than specific LLMs. However, a good prompt is not solely defined by its wording, but also binds to the nature of the LLM in question. In this work, we first quantitatively demonstrate that different prompts should be adapted to different LLMs to enhance their capabilities across various downstream tasks in NLP. Then we novelly propose a model-adaptive prompt optimizer (MAPO) method that optimizes the original prompts for each specific LLM in downstream tasks. Extensive experiments indicate that the proposed method can effectively refine prompts for an LLM, leading to significant improvements over various downstream tasks.
Anthology ID:
2023.findings-emnlp.215
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3279–3304
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.215
DOI:
10.18653/v1/2023.findings-emnlp.215
Bibkey:
Cite (ACL):
Yuyan Chen, Zhihao Wen, Ge Fan, Zhengyu Chen, Wei Wu, Dayiheng Liu, Zhixu Li, Bang Liu, and Yanghua Xiao. 2023. MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3279–3304, Singapore. Association for Computational Linguistics.
Cite (Informal):
MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization (Chen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.215.pdf