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

• URL: http://arxiv.org/abs/2306.11066v2
• Date: Wed, 21 Jun 2023 03:56:39 GMT
• Title: Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
• Authors: Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar
• Abstract summary: State-of-the-art few-shot learning methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. We conduct an extensive study of several state-of-the-art FSL methods to assess their robustness to adversarial perturbations.
• Score: 23.458843951563978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. 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.

Related papers

• Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning [4.137391543972184]
  Semi-supervised learning (SSL) has witnessed remarkable progress, resulting in numerous method variations. In this paper, we present a novel SSL approach named FineSSL that significantly addresses this limitation by adapting pre-trained foundation models. We demonstrate that FineSSL sets a new state of the art for SSL on multiple benchmark datasets, reduces the training cost by over six times, and can seamlessly integrate various fine-tuning and modern SSL algorithms.
  arXiv  Detail & Related papers  (2024-05-20T03:33:12Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• Instance-based Max-margin for Practical Few-shot Recognition [32.26577845735846]
  IbM2 is a novel instance-based max-margin method for few-shot learning. This paper shows that IbM2 almost always leads to improvements compared to its respective baseline methods.
  arXiv  Detail & Related papers  (2023-05-27T04:55:13Z)
• Active Learning Principles for In-Context Learning with Large Language Models [65.09970281795769]
  This paper investigates how Active Learning algorithms can serve as effective demonstration selection methods for in-context learning. We show that in-context example selection through AL prioritizes high-quality examples that exhibit low uncertainty and bear similarity to the test examples.
  arXiv  Detail & Related papers  (2023-05-23T17:16:04Z)
• Alleviating Over-smoothing for Unsupervised Sentence Representation [96.19497378628594]
  We present a Simple method named Self-Contrastive Learning (SSCL) to alleviate this issue. Our proposed method is quite simple and can be easily extended to various state-of-the-art models for performance boosting.
  arXiv  Detail & Related papers  (2023-05-09T11:00:02Z)
• Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples [0.0]
  We aim to train meta-learner models that can leverage prior semantic knowledge about novel classes to guide the classifier synthesis process. In particular, we propose semantically-conditioned feature attention and sample attention mechanisms that estimate the importance of representation dimensions and training instances.
  arXiv  Detail & Related papers  (2022-01-09T16:16:23Z)
• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning [54.617688468341704]
  Few-shot learning aims to learn models that generalize to novel classes with limited training samples. We propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data.
  arXiv  Detail & Related papers  (2021-10-21T13:25:52Z)
• On Data-Augmentation and Consistency-Based Semi-Supervised Learning [77.57285768500225]
  Recently proposed consistency-based Semi-Supervised Learning (SSL) methods have advanced the state of the art in several SSL tasks. Despite these advances, the understanding of these methods is still relatively limited.
  arXiv  Detail & Related papers  (2021-01-18T10:12:31Z)
• Interventional Few-Shot Learning [88.31112565383457]
  We propose a novel Few-Shot Learning paradigm: Interventional Few-Shot Learning. Code is released at https://github.com/yue-zhongqi/ifsl.
  arXiv  Detail & Related papers  (2020-09-28T01:16:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.