Data to 14 Oct 2026

Adversarial Training Methods for Semi-Supervised Text Classification

arXiv 1605.07725 ↗First posted 25 May 2016stat.ML cs.LGcited by 280

Not on the map. Why?

Abstract (arXiv)

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself. The proposed method achieves state of the art results on multiple benchmark semi-supervised and purely supervised tasks. We provide visualizations and analysis showing that the learned word embeddings have improved in quality and that while training, the model is less prone to overfitting. Code is available at https://github.com/tensorflow/models/tree/master/research/adversarial_text.

Key facts. Cited by 280 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 86; 2022: 65; 2023: 56; 2024: 35; 2025: 25; 2026: 11.

280 papers.

Sort:

By area:

2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 469
2021A Survey on Deep Semi-supervised Learningcited by 251
2022Is GPT-3 a Good Data Annotator?cited by 208
2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMcited by 192
2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 165
2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
2021A Survey on Data Augmentation for Text Classificationcited by 111
2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
2021Semantic Communications: Principles and Challengescited by 91
2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89

38 more

2021Towards Improving Adversarial Training of NLP Modelscited by 79
2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 76
2021RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learningcited by 74
2021Towards Robustness Against Natural Language Word Substitutionscited by 69
2024Building Guardrails for Large Language Modelscited by 65
2023Black Box Adversarial Prompting for Foundation Modelscited by 62
2023Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustnesscited by 60
2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
2022Debiased Contrastive Learning of Unsupervised Sentence Representationscited by 56
2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
2022e-CARE: a New Dataset for Exploring Explainable Causal Reasoningcited by 47
2021Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Trainingcited by 41
2022Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learningcited by 41
2023On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codexcited by 41
2021Multi-view Subword Regularizationcited by 40
2021Improved Text Classification via Contrastive Adversarial Trainingcited by 38
2022Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learningcited by 36
2021Defending Against Backdoor Attacks in Natural Language Generationcited by 33
2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
2023Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attackscited by 33
2023Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Informationcited by 33
2021HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizationcited by 32
2021More but Correct: Generating Diversified and Entity-revised Medical Responsecited by 31
2021Enhancing Knowledge Tracing via Adversarial Trainingcited by 31
2024A Survey on Data Augmentation in Large Model Eracited by 31
2023Adversarial Illusions in Multi-Modal Embeddingscited by 29
2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
2021Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Frameworkcited by 28
2021MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillationcited by 27
2021Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answeringcited by 27
2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
2022SEAT: Stable and Explainable Attentioncited by 25
2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 24
2024Avoiding Copyright Infringement via Large Language Model Unlearningcited by 24
2022A Survey of Adversarial Defences and Robustness in NLPcited by 23

50 most cited of 280 All 280 (JSON)