DeepAI AI Chat
Log In Sign Up

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

by   Xiao Liu, et al.
Tsinghua University

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not perform well for normal-sized pre-trained models. We also find that existing methods of prompt tuning cannot handle hard sequence tagging tasks, indicating a lack of universality. We present a novel empirical finding that properly optimized prompt tuning can be universally effective across a wide range of model scales and NLU tasks. It matches the performance of fine-tuning while having only 0.1%-3% tuned parameters. Our method P-Tuning v2 is not a new method, but a version of prefix-tuning <cit.> optimized and adapted for NLU. Given the universality and simplicity of P-Tuning v2, we believe it can serve as an alternative to fine-tuning and a strong baseline for future research.


page 1

page 2

page 3

page 4


Visual Prompt Tuning

The current modus operandi in adapting pre-trained models involves updat...

Better Fine-Tuning by Reducing Representational Collapse

Although widely adopted, existing approaches for fine-tuning pre-trained...

A Kernel-Based View of Language Model Fine-Tuning

It has become standard to solve NLP tasks by fine-tuning pre-trained lan...

When does Parameter-Efficient Transfer Learning Work for Machine Translation?

Parameter-efficient fine-tuning methods (PEFTs) offer the promise of ada...

Parser Training with Heterogeneous Treebanks

How to make the most of multiple heterogeneous treebanks when training a...

GPT Understands, Too

While GPTs with traditional fine-tuning fail to achieve strong results o...

Improving Learning-to-Defer Algorithms Through Fine-Tuning

The ubiquity of AI leads to situations where humans and AI work together...

Code Repositories


A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

view repo


An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

view repo