{"total":96,"rows":[{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2109.00544","title":"Towards Improving Adversarial Training of NLP Models","created":"2021-09-01","cited_by_count":79,"area":null},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2106.08062","title":"SSMix: Saliency-Based Span Mixup for Text Classification","created":"2021-06-15","cited_by_count":39,"area":null},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"area":null},{"id":"2203.07856","title":"Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2205.14690","title":"CoNT: Contrastive Neural Text Generation","created":"2022-05-29","cited_by_count":21,"area":null},{"id":"2109.03079","title":"GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation","created":"2021-09-07","cited_by_count":20,"area":null},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"id":"2108.12589","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-08-28","cited_by_count":18,"area":"synth"},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2210.02952","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","created":"2022-10-06","cited_by_count":15,"area":null},{"id":"2105.02692","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","created":"2021-05-06","cited_by_count":13,"area":null},{"id":"2204.06812","title":"Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation","created":"2022-04-14","cited_by_count":13,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2310.09624","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","created":"2023-10-14","cited_by_count":12,"area":"safety"},{"id":"2211.05561","title":"Estimating Soft Labels for Out-of-Domain Intent Detection","created":"2022-11-10","cited_by_count":11,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2112.11916","title":"ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification","created":"2021-12-16","cited_by_count":10,"area":null},{"id":"2104.01393","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","created":"2021-04-03","cited_by_count":9,"area":null},{"id":"2104.07284","title":"Consistency Training with Virtual Adversarial Discrete Perturbation","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2105.14210","title":"Exploiting Position Bias for Robust Aspect Sentiment Classification","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2211.05523","title":"Impact of Adversarial Training on Robustness and Generalizability of Language Models","created":"2022-11-10","cited_by_count":9,"area":null},{"id":"2404.00415","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","created":"2024-03-30","cited_by_count":9,"area":null},{"id":"2208.01220","title":"GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction","created":"2022-08-02","cited_by_count":8,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2406.04286","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2204.11205","title":"EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification","created":"2022-04-24","cited_by_count":7,"area":null},{"id":"2306.06252","title":"Feature Programming for Multivariate Time Series Prediction","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2402.03325","title":"Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations","created":"2024-01-08","cited_by_count":7,"area":null},{"id":"2112.13969","title":"LINDA: Unsupervised Learning to Interpolate in Natural Language Processing","created":"2021-12-28","cited_by_count":6,"area":null},{"id":"2211.11513","title":"DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2203.09391","title":"When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation","created":"2022-03-17","cited_by_count":5,"area":"distill"},{"id":"2304.08767","title":"Masked Language Model Based Textual Adversarial Example Detection","created":"2023-04-18","cited_by_count":5,"area":null},{"id":"2307.05779","title":"Neural Machine Translation Data Generation and Augmentation using ChatGPT","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2409.03203","title":"An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification","created":"2024-09-05","cited_by_count":5,"area":null},{"id":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2310.07155","title":"\"A Tale of Two Movements\": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Prediction","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2404.00361","title":"Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation","created":"2024-03-30","cited_by_count":4,"area":null},{"id":"2405.08729","title":"Targeted Augmentation for Low-Resource Event Extraction","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2504.08798","title":"Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2202.03651","title":"Causal Scene BERT: Improving object detection by searching for challenging groups of data","created":"2022-02-08","cited_by_count":3,"area":null},{"id":"2202.10948","title":"A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues","created":"2022-02-22","cited_by_count":3,"area":"distill"},{"id":"2206.05790","title":"Data Augmentation for Intent Classification","created":"2022-06-12","cited_by_count":3,"area":null},{"id":"2302.02092","title":"Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics","created":"2023-02-04","cited_by_count":3,"area":null},{"id":"2302.06860","title":"BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction","created":"2023-02-14","cited_by_count":3,"area":"synth"},{"id":"2305.09154","title":"Progressive Translation: Improving Domain Robustness of Neural Machine Translation with Intermediate Sequences","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2305.09598","title":"Boosting Event Extraction with Denoised Structure-to-Text Augmentation","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2312.04032","title":"RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2308.00939","title":"Feature-aware conditional GAN for category text generation","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2310.00734","title":"Robust Sentiment Analysis for Low Resource languages Using Data Augmentation Approaches: A Case Study in Marathi","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2310.06666","title":"Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2404.12014","title":"Enhance Robustness of Language Models Against Variation Attack through Graph Integration","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2107.12329","title":"AASAE: Augmentation-Augmented Stochastic Autoencoders","created":"2021-07-26","cited_by_count":1,"area":null},{"id":"2202.02566","title":"LST: Lexicon-Guided Self-Training for Few-Shot Text Classification","created":"2022-02-05","cited_by_count":1,"area":null},{"id":"2205.09391","title":"Transformers as Neural Augmentors: Class Conditional Sentence Generation via Variational Bayes","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2206.08263","title":"'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2210.02941","title":"BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2210.15944","title":"RoChBert: Towards Robust BERT Fine-tuning for Chinese","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2302.02780","title":"Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2305.13535","title":"Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2306.01931","title":"Simple Data Augmentation Techniques for Chinese Disease Normalization","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2309.03877","title":"Introducing \"Forecast Utterance\" for Conversational Data Science","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2311.02025","title":"Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2405.20602","title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","created":"2024-05-31","cited_by_count":1,"area":"synth"},{"id":"2410.20710","title":"Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2504.15160","title":"The Synthetic Imputation Approach: Generating Optimal Synthetic Texts For Underrepresented Categories In Supervised Classification Tasks","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2505.12317","title":"Improving Out-of-Domain Robustness with Targeted Augmentation in Frequency and Pixel Spaces","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2105.06750","title":"Out-of-Manifold Regularization in Contextual Embedding Space for Text Classification","created":"2021-05-14","cited_by_count":0,"area":null},{"id":"2305.02858","title":"ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2305.19617","title":"MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2306.14377","title":"Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2307.00008","title":"Investigating Masking-based Data Generation in Language Models","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2307.10457","title":"Improving the Reusability of Pre-trained Language Models in Real-world Applications","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2402.12513","title":"Induced Model Matching: Restricted Models Help Train Full-Featured Models","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2410.09038","title":"SimpleStrat: Diversifying Language Model Generation with Stratification","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2503.16550","title":"Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2504.18839","title":"Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents","created":"2025-04-26","cited_by_count":0,"area":"agents"},{"id":"2511.11286","title":"D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2607.22924","title":"Layering Virtual Try-On","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.00082","title":"KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.15757","title":"Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.15761","title":"Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}