Reducing Retraining by Recycling Parameter-Efficient Prompts

Parameter-efficient methods are able to use a single frozen pre-trained large language model to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text.

Data and Resources

Cite this as

Brian Lester, Joshua Yurtsever, Siamak Shakeri, Noah Constant (2024). Dataset: Reducing Retraining by Recycling Parameter-Efficient Prompts. https://doi.org/10.57702/v7rs054o

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2208.05577
Author Brian Lester
More Authors
Joshua Yurtsever
Siamak Shakeri
Noah Constant
Homepage https://github.com/google-research/prompt-tuning/tree/main/prompt_tuning/recycling