{"total":104,"rows":[{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130,"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":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2306.05225","title":"Boosting Adversarial Transferability by Achieving Flat Local Maxima","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2212.02974","title":"CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain","created":"2022-12-06","cited_by_count":31,"area":null},{"id":"2212.10888","title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2304.02858","title":"A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation","created":"2023-04-06","cited_by_count":25,"area":null},{"id":"2301.02830","title":"Image Data Augmentation Approaches: A Comprehensive Survey and Future directions","created":"2023-01-07","cited_by_count":23,"area":null},{"id":"2501.18845","title":"Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities","created":"2025-01-31","cited_by_count":22,"area":null},{"id":"2310.18365","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2109.03777","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","created":"2021-09-08","cited_by_count":17,"area":null},{"id":"2404.17642","title":"Empowering Large Language Models for Textual Data Augmentation","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2212.07050","title":"Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2302.09795","title":"Simple Disentanglement of Style and Content in Visual Representations","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2307.10792","title":"Optimizing PatchCore for Few/many-shot Anomaly Detection","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2303.09767","title":"It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness","created":"2023-03-17","cited_by_count":9,"area":null},{"id":"2309.00300","title":"Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2401.11105","title":"Are Latent Vulnerabilities Hidden Gems for Software Vulnerability Prediction? An Empirical Study","created":"2024-01-20","cited_by_count":9,"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":"2205.09229","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","created":"2022-05-18","cited_by_count":7,"area":null},{"id":"2405.12630","title":"Exploration of Masked and Causal Language Modelling for Text Generation","created":"2024-05-21","cited_by_count":7,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2407.10722","title":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2410.18378","title":"Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning","created":"2024-10-24","cited_by_count":6,"area":null},{"id":"2506.06580","title":"AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture","created":"2025-06-06","cited_by_count":6,"area":null},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2202.08835","title":"General Cyclical Training of Neural Networks","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2204.04711","title":"Data Augmentation for Biomedical Factoid Question Answering","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2209.01560","title":"Selective Text Augmentation with Word Roles for Low-Resource Text Classification","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2207.11076","title":"Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence","created":"2022-07-22","cited_by_count":4,"area":null},{"id":"2212.09670","title":"StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2309.04862","title":"Distributional Data Augmentation Methods for Low Resource Language","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2201.11294","title":"Highly Generalizable Models for Multilingual Hate Speech Detection","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2305.09608","title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2310.05210","title":"TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining","created":"2023-10-08","cited_by_count":3,"area":null},{"id":"2311.12735","title":"LowResource at BLP-2023 Task 2: Leveraging BanglaBert for Low Resource Sentiment Analysis of Bangla Language","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2312.16563","title":"RDGCL: Reaction-Diffusion Graph Contrastive Learning for Recommendation","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2402.15525","title":"Detecting misinformation through Framing Theory: the Frame Element-based Model","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2412.00324","title":"Table Integration in Data Lakes Unleashed: Pairwise Integrability Judgment, Integrable Set Discovery, and Multi-Tuple Conflict Resolution","created":"2024-11-30","cited_by_count":3,"area":null},{"id":"2412.02108","title":"Evaluating the Impact of Data Augmentation on Predictive Model Performance","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2306.07737","title":"Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2307.16609","title":"Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks","created":"2023-07-31","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":"2405.10633","title":"Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networks","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2409.15848","title":"iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2204.03954","title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2204.12024","title":"Reprint: a randomized extrapolation based on principal components for data augmentation","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2210.02143","title":"Common Vulnerability Scoring System Prediction based on Open Source Intelligence Information Sources","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2304.04212","title":"RISC: Generating Realistic Synthetic Bilingual Insurance Contract","created":"2023-04-09","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2307.04468","title":"Badgers: generating data quality deficits with Python","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2307.12564","title":"Towards Generalising Neural Topical Representations","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2310.17015","title":"Data Augmentation for Emotion Detection in Small Imbalanced Text Data","created":"2023-10-25","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":"2312.17278","title":"Large Language Models for Conducting Advanced Text Analytics Information Systems Research","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2402.05584","title":"AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2412.04673","title":"Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2503.15133","title":"EmoGRACE: Aspect-based emotion analysis for social media data","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2504.06917","title":"Data Augmentation for Fake Reviews Detection in Multiple Languages and Multiple Domains","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2507.22729","title":"Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2509.16813","title":"Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition-Informed Approach to Quantifying Identity Fusion from Text","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2512.10178","title":"CIEGAD: Cluster-Conditioned Interpolative and Extrapolative Framework for Geometry-Aware and Domain-Aligned Data Augmentation","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2605.01292","title":"Addressing Data Scarcity in Bangla Fake News Detection: An LLM-Based Dataset Augmentation Approach","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2207.09728","title":"Revisiting data augmentation for subspace clustering","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2210.04756","title":"Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2212.10558","title":"On-the-fly Denoising for Data Augmentation in Natural Language Understanding","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2303.02758","title":"WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2309.12763","title":"Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2309.16175","title":"Using Weak Supervision and Data Augmentation in Question Answering","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2310.07306","title":"SNOiC: Soft Labeling and Noisy Mixup based Open Intent Classification Model","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2402.06766","title":"Evaluation Metrics for Text Data Augmentation in NLP","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2403.12468","title":"CrossTune: Black-Box Few-Shot Classification with Label Enhancement","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2406.00393","title":"Gender Bias Detection in Court Decisions: A Brazilian Case Study","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2407.18442","title":"Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity Recognition","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2408.10516","title":"Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2409.17474","title":"Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.08053","title":"A Target-Aware Analysis of Data Augmentation for Hate Speech Detection","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2412.15831","title":"Enriching Social Science Research via Survey Item Linking","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2501.03139","title":"VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2501.05497","title":"Spatial Information Integration in Small Language Models for Document Layout Generation and Classification","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2501.11293","title":"A Machine Learning Framework for Handling Unreliable Absence Label and Class Imbalance for Marine Stinger Beaching Prediction","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2503.04279","title":"Dual-Class Prompt Generation: Enhancing Indonesian Gender-Based Hate Speech Detection through Data Augmentation","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2506.14583","title":"Synthetic Data Augmentation for Table Detection: Re-evaluating TableNet's Performance with Automatically Generated Document Images","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2508.14723","title":"Transplant Then Regenerate: A New Paradigm for Text Data Augmentation","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.02332","title":"Extrapolated Markov Chain Oversampling Method for Imbalanced Text Classification","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.22405","title":"Knowledge-guided Continual Learning for Behavioral Analytics Systems","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2511.12180","title":"Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.17092","title":"Data Augmentation Supporting a Conversational Agent Designed for Smoking Cessation Support Groups","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.04698","title":"Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.12540","title":"When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14163","title":"SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.19754","title":"Exploring Data Augmentation and Resampling Strategies for Transformer-Based Models to Address Class Imbalance in AI Scoring of Scientific Explanations in NGSS Classroom","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2605.01073","title":"Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing","created":"2026-05-01","cited_by_count":0,"area":null}],"next_cursor":"100"}