Prompt and Parameter Co-Optimization for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bo, Xiaohe, Li, Rui, Sun, Zexu, Dai, Quanyu, Zhang, Zeyu, Tian, Zihang, Chen, Xu, Dong, Zhenhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914362761936896
author Bo, Xiaohe
Li, Rui
Sun, Zexu
Dai, Quanyu
Zhang, Zeyu
Tian, Zihang
Chen, Xu
Dong, Zhenhua
author_facet Bo, Xiaohe
Li, Rui
Sun, Zexu
Dai, Quanyu
Zhang, Zeyu
Tian, Zihang
Chen, Xu
Dong, Zhenhua
contents Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language, and the latter through implicit parameter updates. However, prior work has typically studied them in isolation, leaving their synergistic potential largely underexplored. To bridge this gap, in this paper, we introduce MetaTuner, a novel framework that jointly integrates prompt optimization and fine-tuning for LLM training. Specifically, we introduce two neural networks to generate prompts and parameters, respectively, while allowing them to share a common bottom encoding layer to enable knowledge sharing. By the guidance of the final supervised signals, our framework is optimized to discover the optimal combinations between the prompts and parameters. Given that prompt learning involves discrete optimization while fine-tuning operates in a continuous parameter space, we design a supervised regularization loss to train our framework effectively. Extensive experiments across diverse benchmarks show that our method consistently outperforms the baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24245
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt and Parameter Co-Optimization for Large Language Models
Bo, Xiaohe
Li, Rui
Sun, Zexu
Dai, Quanyu
Zhang, Zeyu
Tian, Zihang
Chen, Xu
Dong, Zhenhua
Computation and Language
Artificial Intelligence
Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language, and the latter through implicit parameter updates. However, prior work has typically studied them in isolation, leaving their synergistic potential largely underexplored. To bridge this gap, in this paper, we introduce MetaTuner, a novel framework that jointly integrates prompt optimization and fine-tuning for LLM training. Specifically, we introduce two neural networks to generate prompts and parameters, respectively, while allowing them to share a common bottom encoding layer to enable knowledge sharing. By the guidance of the final supervised signals, our framework is optimized to discover the optimal combinations between the prompts and parameters. Given that prompt learning involves discrete optimization while fine-tuning operates in a continuous parameter space, we design a supervised regularization loss to train our framework effectively. Extensive experiments across diverse benchmarks show that our method consistently outperforms the baselines.
title Prompt and Parameter Co-Optimization for Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.24245