Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lan, Pengxiang, Xu, Haoyu, Yang, Enneng, Liang, Yuliang, Guo, Guibing, Zhao, Jianzhe, Wang, Xingwei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917927250296832
author Lan, Pengxiang
Xu, Haoyu
Yang, Enneng
Liang, Yuliang
Guo, Guibing
Zhao, Jianzhe
Wang, Xingwei
author_facet Lan, Pengxiang
Xu, Haoyu
Yang, Enneng
Liang, Yuliang
Guo, Guibing
Zhao, Jianzhe
Wang, Xingwei
contents Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: (i) They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. (ii) Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correlates positively with memory usage and computational costs. Achieving high efficiency and performance remains an ongoing challenge. To address these issues, we propose a novel Low-parameters prompt tuning (LAMP) method, which leverages prompt decomposition and compressed outer product. Specifically, the prompt decomposition module employs Truncated SVD to reduce training parameters and significantly lower the dimensionality of the soft prompt parameter space. It then utilizes a compressed outer product module to facilitate multiple interactions among prompt tokens, exploring their intrinsic associations to enhance knowledge representation. Finally, LAMP uses average pooling to reduce memory usage and training/inference time. Extensive experiments across six architectures and eight datasets demonstrate that LAMP outperforms state-of-the-art PT-based and LoRA-based methods in performance and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
Lan, Pengxiang
Xu, Haoyu
Yang, Enneng
Liang, Yuliang
Guo, Guibing
Zhao, Jianzhe
Wang, Xingwei
Computation and Language
Artificial Intelligence
Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: (i) They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. (ii) Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correlates positively with memory usage and computational costs. Achieving high efficiency and performance remains an ongoing challenge. To address these issues, we propose a novel Low-parameters prompt tuning (LAMP) method, which leverages prompt decomposition and compressed outer product. Specifically, the prompt decomposition module employs Truncated SVD to reduce training parameters and significantly lower the dimensionality of the soft prompt parameter space. It then utilizes a compressed outer product module to facilitate multiple interactions among prompt tokens, exploring their intrinsic associations to enhance knowledge representation. Finally, LAMP uses average pooling to reduce memory usage and training/inference time. Extensive experiments across six architectures and eight datasets demonstrate that LAMP outperforms state-of-the-art PT-based and LoRA-based methods in performance and efficiency.
title Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.12200