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

By Xiao Liu, Kaixuan Ji, Yicheng Fu, W. Tam, Zhengxiao Du, Zhilin Yang, Jie Tang. 2022

1,117 citations recorded by the source corpus.

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 pretrained models. We also find that existing methods of prompt tuning cannot handle hard sequence labeling 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 finetuning while having only 0.1%-3% tuned parameters. Our method P-Tuning v2 is an implementation of Deep Prompt Tuning (CITATION) optimized and adapted for NLU. Given the universality and simplicity of P-Tuning v2, we believe it can serve as an alternative to finetuning and a strong baseline for future research.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Prompting & Reasoning, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jie Tang
  2. Ming Ding
  3. Steven C. H. Hoi
  4. Xiao Liu
  5. Junnan Li
  6. Mohit Bansal
  7. Yuxiao Dong
  8. Jianfeng Gao

In Electrical and Electronic Engineering

  1. Matei A. Zaharia
  2. Ming Ding
  3. Steven C. H. Hoi
  4. Ajmal Saeed Mian
  5. Tianjun Zhang
  6. Xia Hu
  7. Ion Stoica
  8. Traian Rebedea

In Prompting & Reasoning

  1. Jie Tang
  2. Matei A. Zaharia
  3. Ming Ding
  4. Steven C. H. Hoi
  5. Xiao Liu
  6. Ziqi Zhou
  7. Lingqiao Liu
  8. Sheng Shen

In Efficiency & Compression

  1. Ion Stoica
  2. Joseph E. Gonzalez
  3. Matei A. Zaharia
  4. Akhilesh Deepak Gotmare
  5. Ming Ding
  6. Nick Barnes
  7. Steven C. H. Hoi
  8. Ajmal Saeed Mian

Citations in the corpus