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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yuyan, Wen, Zhihao, Fan, Ge, Chen, Zhengyu, Wu, Wei, Liu, Dayiheng, Li, Zhixu, Liu, Bang, Xiao, Yanghua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913418029563904
author Chen, Yuyan
Wen, Zhihao
Fan, Ge
Chen, Zhengyu
Wu, Wei
Liu, Dayiheng
Li, Zhixu
Liu, Bang
Xiao, Yanghua
author_facet Chen, Yuyan
Wen, Zhihao
Fan, Ge
Chen, Zhengyu
Wu, Wei
Liu, Dayiheng
Li, Zhixu
Liu, Bang
Xiao, Yanghua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04118
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
Chen, Yuyan
Wen, Zhihao
Fan, Ge
Chen, Zhengyu
Wu, Wei
Liu, Dayiheng
Li, Zhixu
Liu, Bang
Xiao, Yanghua
Computation and Language
Artificial Intelligence
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.
title MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.04118