{"total":52,"rows":[{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154,"area":"synth"},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","cited_by_count":33,"area":"synth"},{"id":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"area":"synth"},{"id":"2110.01256","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","created":"2021-10-04","cited_by_count":23,"area":"synth"},{"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":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2406.12480","title":"The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions","created":"2024-06-18","cited_by_count":16,"area":"synth"},{"id":"2304.01228","title":"Better Language Models of Code through Self-Improvement","created":"2023-04-02","cited_by_count":14,"area":"synth"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2410.15234","title":"Bias Amplification: Large Language Models as Increasingly Biased Media","created":"2024-10-19","cited_by_count":12,"area":"synth"},{"id":"2110.06274","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","created":"2021-10-12","cited_by_count":9,"area":"synth"},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","cited_by_count":9,"area":"synth"},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2410.10864","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","created":"2024-10-07","cited_by_count":8,"area":"synth"},{"id":"2508.10027","title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","created":"2025-08-08","cited_by_count":8,"area":"synth"},{"id":"2210.16613","title":"Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers","created":"2022-10-29","cited_by_count":7,"area":"synth"},{"id":"2404.02422","title":"Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data","created":"2024-04-03","cited_by_count":7,"area":"synth"},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2101.04758","title":"Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling","created":"2021-01-12","cited_by_count":6,"area":"synth"},{"id":"2103.07449","title":"Cooperative Self-training of Machine Reading Comprehension","created":"2021-03-12","cited_by_count":5,"area":"synth"},{"id":"2412.04573","title":"Give me Some Hard Questions: Synthetic Data Generation for Clinical QA","created":"2024-12-05","cited_by_count":5,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2503.22006","title":"Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them","created":"2025-03-27","cited_by_count":4,"area":"synth"},{"id":"2306.06347","title":"DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies","created":"2023-06-10","cited_by_count":3,"area":"synth"},{"id":"2310.01119","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","created":"2023-10-02","cited_by_count":3,"area":"synth"},{"id":"2310.13022","title":"Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding","created":"2023-10-19","cited_by_count":3,"area":"synth"},{"id":"2404.08078","title":"SQBC: Active Learning using LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions","created":"2024-04-11","cited_by_count":3,"area":"synth"},{"id":"2406.06056","title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","created":"2024-06-10","cited_by_count":3,"area":"synth"},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2309.08777","title":"Self-training Strategies for Sentiment Analysis: An Empirical Study","created":"2023-09-15","cited_by_count":2,"area":"synth"},{"id":"2112.08787","title":"AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models","created":"2021-12-16","cited_by_count":1,"area":"synth"},{"id":"2411.00533","title":"ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models","created":"2024-11-01","cited_by_count":1,"area":"synth"},{"id":"2503.20588","title":"Synthetic Data Augmentation for Cross-domain Implicit Discourse Relation Recognition","created":"2025-03-26","cited_by_count":1,"area":"synth"},{"id":"2504.03877","title":"Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesis","created":"2025-04-04","cited_by_count":1,"area":"synth"},{"id":"2504.20921","title":"Leveraging Generative AI Through Prompt Engineering and Rigorous Validation to Create Comprehensive Synthetic Datasets for AI Training in Healthcare","created":"2025-04-29","cited_by_count":1,"area":"synth"},{"id":"2508.12482","title":"The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping","created":"2025-08-17","cited_by_count":1,"area":"synth"},{"id":"2306.10414","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","created":"2023-06-17","cited_by_count":0,"area":"synth"},{"id":"2310.19420","title":"Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings","created":"2023-10-30","cited_by_count":0,"area":"synth"},{"id":"2312.04982","title":"Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification","created":"2023-12-08","cited_by_count":0,"area":"synth"},{"id":"2403.01163","title":"BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses","created":"2024-03-02","cited_by_count":0,"area":"synth"},{"id":"2511.09539","title":"SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim Verification","created":"2025-11-12","cited_by_count":0,"area":"synth"},{"id":"2605.07201","title":"PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat","created":"2026-05-08","cited_by_count":0,"area":"synth"},{"id":"2606.18235","title":"EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation","created":"2026-06-16","cited_by_count":0,"area":"synth"},{"id":"2609.39447","title":"Synthetic Data Characterization via Training Dynamics","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}