ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2406.05279
24
0

SuperPos-Prompt: Enhancing Soft Prompt Tuning of Language Models with Superposition of Multi Token Embeddings

7 June 2024
MohammadAli SadraeiJavaeri
Ehsaneddin Asgari
A. Mchardy
Hamid R. Rabiee
    VLM
    AAML
ArXivPDFHTML
Abstract

Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their growing use, achieving optimal tuning with soft prompts, especially for smaller datasets, remains a substantial challenge. This study makes two contributions in this domain: (i) we introduce SuperPos-Prompt, a new reparameterization technique employing the superposition of multiple pretrained vocabulary embeddings to improve the learning of soft prompts. Our experiments across several GLUE and SuperGLUE benchmarks consistently highlight SuperPos-Prompt's superiority over Residual Prompt tuning, exhibiting an average score increase of +6.4+6.4+6.4 in T5-Small and +5.0+5.0+5.0 in T5-Base along with a faster convergence. Remarkably, SuperPos-Prompt occasionally outperforms even full fine-tuning methods. (ii) Additionally, we demonstrate enhanced performance and rapid convergence by omitting dropouts from the frozen network, yielding consistent improvements across various scenarios and tuning methods.

View on arXiv
Comments on this paper