Decrease the Prompt Uncertainty: Adversarial Prompt Learning for Few-shot Text Classification

Jinta Weng, Zhaoguang Zhang, Jing Yaqi*, Chenxu Niu, Heyan Huang*, Yue Hu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With few-shot learning abilities, pre-trained language models (PLMs) have achieved remarkable success in classification tasks. However, recent studies have shown that the performance of PLM is vulnerable due to different prompts and the instability of the prompt-based learning process. To address this challenge, we explore appropriate perturbation addition of adversarial training and integrate the global knowledge of the full-parameter fine-tuned pre-trained language model(PLM). Specifically, we propose an adversarial prompt learning model (ATPET) and ATPET with fine-tuning(ATPET-FT), incorporating ATPET with fine-tuning knowledge into the prompt learning process. Through extensive experiments on several few-shot classification tasks and challenging data settings, we demonstrate that our methods consistently improve the robustness while maintaining the effectiveness of PLMs.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1230-1236
Number of pages7
ISBN (Electronic)9781665410205
DOIs
Publication statusPublished - 2024
Event2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024 - Kuching, Malaysia
Duration: 6 Oct 202410 Oct 2024

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X

Conference

Conference2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024
Country/TerritoryMalaysia
CityKuching
Period6/10/2410/10/24

Fingerprint

Dive into the research topics of 'Decrease the Prompt Uncertainty: Adversarial Prompt Learning for Few-shot Text Classification'. Together they form a unique fingerprint.

Cite this