Challenge: Existing methods for regularizing a model are agnostic to the training model and may not be effective for perturbed inputs.
Approach: They propose an augmentation method of adding a discrete noise that would incur the highest divergence between predictions by replacing tokens while keeping original semantics.
Outcome: The proposed method outperforms baselines on semi-supervised text classification tasks and a robustness benchmark.

Similar Papers

Achieving Model Robustness through Discrete Adversarial Training (2021.emnlp-main)

Copied to clipboard

Challenge: Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to predicting error.
Approach: They propose a discrete adversarial attack based on best-first search and random sampling attacks that are not based upon expensive search procedures.
Outcome: The proposed attack outperforms offline augmentation and speedups on three datasets.
Generative Adversarial Training with Perturbed Token Detection for Model Robustness (2023.emnlp-main)

Copied to clipboard

Challenge: Existing adversarial training methods use discrete tokens to deceive models . current approaches use embeddings, whereas actual text-based training uses discrete text tokens.
Approach: They propose a framework that integrates gradient-based learning, adversarial example generation and perturbed token detection to enhance adversariarial robustness.
Outcome: The proposed framework surpasses the state-of-the-art results of ChatGPT by 10% in average accuracy.
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models (2021.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that powerful pre-trained language models can be fooled by small perturbations or intentional attacks.
Approach: They propose a framework for fine-tuning PLMs using a masked language model and Gaussian noise to augment semantically relevant examples with sufficient diversity.
Outcome: The proposed framework improves the robustness of pre-trained language models and alleviates performance degradation under adversarial attacks.
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Abstractive summarization models often produce inconsistent statements or false facts.
Approach: They propose an efficient weak-supervised adversarial data augmentation approach to generate factual consistency datasets by backpropagating gradients on token embeddings.
Outcome: The proposed model can make interpretable factual errors tracing on public datasets and is cost-effective.
Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods augment input sequence with token replacement, assuming annotations on the replaced positions are unchanged.
Approach: They propose to use paraphrasing to enhance unsupervised consistency training by replacing tokens with augmented data.
Outcome: The proposed method is especially effective when annotations are limited.
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models (2022.emnlp-main)

Copied to clipboard

Challenge: Traditional adversarial examples involve finding a small perturbation that does not change an input’s true label but confuses the classifier into outputting a different prediction.
Approach: They propose to use contrastive learning to increase model robustness against fickle adversarial examples by reducing the vulnerability of adversarials to fickle ones.
Outcome: The proposed method improves model robustness against fickle and obstinate adversarial examples.
Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training (N19-1)

Copied to clipboard

Challenge: Recent work has shown superior performance for non-adversarial methods in more challenging language pairs.
Approach: They propose to use adversarial autoencoder to map monolingual embeddings to a shared space and to put the target encoders as an adversary against the corresponding discriminator.
Outcome: The proposed method is more robust and achieves better performance than previously proposed adversarial and non-adversarial methods.
Impact of Adversarial Training on Robustness and Generalizability of Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Adversarial training is widely acknowledged as the most effective defense against adversarial attacks, but achieving both robustness and generalization requires a trade-off.
Approach: They propose to compare pre-training data augmentation and training time input perturbations with embedding space perturbations to find out whether they improve generalization.
Outcome: The proposed methods improve generalization and robustness of the trained models.
READ: Improving Relation Extraction from an ADversarial Perspective (2024.findings-naacl)

Copied to clipboard

Challenge: Recent work in relation extraction (RE) has high generalization capability, but adversarial training methods rely on entities.
Approach: They propose an adversarial training method specifically designed for relation extraction that introduces sequence- and token-level perturbations to the sample and uses a separate perturbation vocabulary to improve the search for entity and context perturbations.
Outcome: The proposed method significantly improves accuracy and robustness in low-resource scenarios.
Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training (2021.acl-long)

Copied to clipboard

Challenge: Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better.
Approach: They propose an algorithm that encourages the model to be sensitive to perturbations in dialogue history and learn from perturbations.
Outcome: The proposed approach can model dialogue history better and generate more diverse responses on two benchmark datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations