Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach #2119

Open
icoxfog417 opened this issue Nov 9, 2023 · 1 comment

Comments

@icoxfog417
Copy link
Member

icoxfog417 commented Nov 9, 2023

一言でいうと

良質なデータを収集することで少量で高い転移学習性能を獲得する試み。事前学習済みモデルにプロンプトを与えデータの疑似ラベルを予測し、予測分布が一様で不確実性が高いデータを学習効果が高いとみなす。ベクトル空間上の距離をもとに周辺データも不確実性が高く、かつ採用するデータ間の距離が近すぎないよう調整し選択する。128 ラベルデータでフル学習の 90% 超の精度を達成。

論文リンク

https://arxiv.org/abs/2209.06995

著者/所属機関

Yue Yu, Rongzhi Zhang, Ran Xu, Jieyu Zhang, Jiaming Shen, Chao Zhang

  • Georgia Institute of Technology
  • Emory University
  • University of Washington
  • Google

投稿日付(yyyy/MM/dd)

2022/9/15

概要

新規性・差分

手法

結果

コメント

@icoxfog417
Copy link
Member Author

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant