LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Shouchang, Damani, Sonam, Chang, Keng-hao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914850904473600
author Guo, Shouchang
Damani, Sonam
Chang, Keng-hao
author_facet Guo, Shouchang
Damani, Sonam
Chang, Keng-hao
contents In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This approach eliminates the need for hand-crafted prompt engineering or explicit model fine-tuning. Prompt tuning is significantly more parameter-efficient than model fine-tuning, as it involves optimizing partial inputs of language models to produce desired outputs. In this work, we aim to further reduce the amount of trainable parameters required for a language model to perform well on specific tasks. We propose Low-rank Prompt Tuning (LoPT), a low-rank model for prompts that achieves efficient prompt optimization. The proposed method demonstrates similar outcomes to full parameter prompt tuning while reducing the number of trainable parameters by a factor of 5. It also provides promising results compared to the state-of-the-art methods that would require 10 to 20 times more parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19486
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Models
Guo, Shouchang
Damani, Sonam
Chang, Keng-hao
Computation and Language
Artificial Intelligence
Emerging Technologies
Machine Learning
Signal Processing
In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This approach eliminates the need for hand-crafted prompt engineering or explicit model fine-tuning. Prompt tuning is significantly more parameter-efficient than model fine-tuning, as it involves optimizing partial inputs of language models to produce desired outputs. In this work, we aim to further reduce the amount of trainable parameters required for a language model to perform well on specific tasks. We propose Low-rank Prompt Tuning (LoPT), a low-rank model for prompts that achieves efficient prompt optimization. The proposed method demonstrates similar outcomes to full parameter prompt tuning while reducing the number of trainable parameters by a factor of 5. It also provides promising results compared to the state-of-the-art methods that would require 10 to 20 times more parameters.
title LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Models
topic Computation and Language
Artificial Intelligence
Emerging Technologies
Machine Learning
Signal Processing
url https://arxiv.org/abs/2406.19486