{"total":94,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208,"area":null},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2408.00818","title":"Y Social: an LLM-powered Social Media Digital Twin","created":"2024-08-01","cited_by_count":44,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"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":"2306.15766","title":"Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost","created":"2023-06-27","cited_by_count":33,"area":null},{"id":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32,"area":null},{"id":"2203.10652","title":"Continual Sequence Generation with Adaptive Compositional Modules","created":"2022-03-20","cited_by_count":31,"area":null},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30,"area":null},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26,"area":null},{"id":"2404.13812","title":"A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation","created":"2024-04-22","cited_by_count":21,"area":null},{"id":"2107.09539","title":"Parametric Scattering Networks","created":"2021-07-20","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2109.00523","title":"Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification","created":"2021-09-01","cited_by_count":15,"area":null},{"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":"2401.01053","title":"Cheetah: Natural Language Generation for 517 African Languages","created":"2024-01-02","cited_by_count":15,"area":null},{"id":"2407.21523","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","created":"2024-07-31","cited_by_count":15,"area":null},{"id":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2111.09618","title":"To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP","created":"2021-11-18","cited_by_count":12,"area":null},{"id":"2107.05295","title":"DaCy: A Unified Framework for Danish NLP","created":"2021-07-12","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":"2202.08063","title":"Information Extraction in Low-Resource Scenarios: Survey and Perspective","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"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":"2203.11670","title":"Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation","created":"2022-03-22","cited_by_count":8,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","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":"2410.17555","title":"FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning","created":"2024-10-23","cited_by_count":8,"area":null},{"id":"2112.10064","title":"Data Augmentation for Mental Health Classification on Social Media","created":"2021-12-19","cited_by_count":7,"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":"2206.12879","title":"Data Augmentation for Dementia Detection in Spoken Language","created":"2022-06-26","cited_by_count":7,"area":null},{"id":"2210.16838","title":"Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2309.09582","title":"Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.00303","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","created":"2024-03-30","cited_by_count":7,"area":null},{"id":"2406.19614","title":"A Survey on Data Quality Dimensions and Tools for Machine Learning","created":"2024-06-28","cited_by_count":7,"area":null},{"id":"2407.00100","title":"Enhancing In-Context Learning via Implicit Demonstration Augmentation","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2407.05006","title":"Recent Advancements and Challenges of Turkic Central Asian Language Processing","created":"2024-07-06","cited_by_count":6,"area":null},{"id":"2204.12421","title":"Disambiguation of morpho-syntactic features of African American English -- the case of habitual be","created":"2022-04-26","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":"2305.10647","title":"BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2412.13860","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2301.03403","title":"A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2304.09402","title":"MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2410.18390","title":"Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.15518","title":"DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection","created":"2026-05-15","cited_by_count":4,"area":null},{"id":"2109.09825","title":"Data Augmentation Methods for Anaphoric Zero Pronouns","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2203.10693","title":"Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2212.13939","title":"Data Augmentation using Transformers and Similarity Measures for Improving Arabic Text Classification","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2303.09719","title":"Learning towards Selective Data Augmentation for Dialogue Generation","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2305.13658","title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2308.06507","title":"AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2408.14595","title":"Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2411.11668","title":"Efficient and Robust Continual Graph Learning for Graph Classification in Biology","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2411.14896","title":"Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2210.03123","title":"On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2402.14895","title":"On Evaluation Protocols for Data Augmentation in a Limited Data Scenario","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2403.02271","title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2503.03705","title":"Enhancing LLM Knowledge Learning through Generalization","created":"2025-03-05","cited_by_count":2,"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":"2309.06550","title":"Synthetic Text Generation using Hypergraph Representations","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2309.12273","title":"Improving VTE Identification through Adaptive NLP Model Selection and Clinical Expert Rule-based Classifier from Radiology Reports","created":"2023-09-21","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":"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":"2404.12659","title":"SOS-1K: A Fine-grained Suicide Risk Classification Dataset for Chinese Social Media Analysis","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2410.06370","title":"HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2504.07024","title":"Data Augmentation and Hyperparameter Tuning for Low-Resource MFA","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2604.18759","title":"Model-Agnostic Meta Learning for Class Imbalance Adaptation","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2110.07096","title":"Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts","created":"2021-10-14","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":"2306.04823","title":"Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2306.16644","title":"Probabilistic Linguistic Knowledge and Token-level Text Augmentation","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2309.06527","title":"Machine Translation Models Stand Strong in the Face of Adversarial Attacks","created":"2023-09-10","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":"2310.11607","title":"TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2410.03194","title":"Parallel Corpus Augmentation using Masked Language Models","created":"2024-10-04","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":"2502.16022","title":"Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study","created":"2025-02-22","cited_by_count":0,"area":null},{"id":"2506.22491","title":"PromptAug: Fine-grained Conflict Classification Using Data Augmentation","created":"2025-06-24","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":"2509.21530","title":"Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.06772","title":"Calibrating Generative AI to Produce Realistic Essays for Data Augmentation","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.07218","title":"Collaborative and Efficient Fine-tuning: Leveraging Task Similarity","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.17366","title":"RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.07015","title":"Corpora deduplication or duplication in Natural Language Processing of few resourced languages ? A case of study: The Mexico's Nahuatl","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.10938","title":"A Systematic Approach for Selecting Trajectories for Data Augmentation","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.16212","title":"Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.12340","title":"Class-Structure Preservation Beats Diversity: A Comprehensive Benchmark of Text Augmentation Methods for Imbalanced Text Classification","created":"2026-06-03","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}],"next_cursor":null}