Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding

Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar


Abstract
State-of-the-art few-shot learning (FSL) methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. While much of the prior FSL methods focus on improving downstream task performance, there is a limited understanding of the adversarial robustness of such methods. In this work, we conduct an extensive study of several state-of-the-art FSL methods to assess their robustness to adversarial perturbations. To better understand the impact of various factors towards robustness (or the lack of it), we evaluate prompt-based FSL methods against fully fine-tuned models for aspects such as the use of unlabeled data, multiple prompts, number of few-shot examples, model size and type. Our results on six GLUE tasks indicate that compared to fully fine-tuned models, vanilla FSL methods lead to a notable relative drop in task performance (i.e., are less robust) in the face of adversarial perturbations. However, using (i) unlabeled data for prompt-based FSL and (ii) multiple prompts flip the trend – the few-shot learning approaches demonstrate a lesser drop in task performance than fully fine-tuned models. We further demonstrate that increasing the number of few-shot examples and model size lead to increased adversarial robustness of vanilla FSL methods. Broadly, our work sheds light on the adversarial robustness evaluation of prompt-based FSL methods for NLU tasks.
Anthology ID:
2023.findings-acl.138
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2196–2208
Language:
URL:
https://aclanthology.org/2023.findings-acl.138
DOI:
10.18653/v1/2023.findings-acl.138
Bibkey:
Cite (ACL):
Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, and Srijan Kumar. 2023. Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2196–2208, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding (Nookala et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.138.pdf