Log In Sign Up

The Power of Scale for Parameter-Efficient Prompt Tuning

by   Brian Lester, et al.

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signal from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3's "few-shot" learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method "closes the gap" and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant in that large models are costly to share and serve, and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed "prefix tuning" of Li and Liang (2021), and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer, as compared to full model tuning.


page 5

page 7


PPT: Pre-trained Prompt Tuning for Few-shot Learning

Prompts for pre-trained language models (PLMs) have shown remarkable per...

SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer

As pre-trained language models have gotten larger, there has been growin...

STT: Soft Template Tuning for Few-Shot Adaptation

Prompt tuning has been an extremely effective tool to adapt a pre-traine...

Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning

Prompt tuning approaches, which learn task-specific soft prompts for a d...

XPrompt: Exploring the Extreme of Prompt Tuning

Prompt tuning learns soft prompts to condition frozen Pre-trained Langua...

Variational prompt tuning improves generalization of vision-language models

Prompt tuning provides an efficient mechanism to adapt large vision-lang...

RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning

Prompting has shown impressive success in enabling large pretrained lang...