{"total":25,"rows":[{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187,"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":"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":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"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":"2310.00646","title":"Source Attribution for Large Language Model-Generated Data","created":"2023-10-01","cited_by_count":11,"area":"synth"},{"id":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","cited_by_count":10,"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":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"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":"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":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"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":"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":"2401.00575","title":"Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets","created":"2023-12-31","cited_by_count":2,"area":"synth"},{"id":"2405.14212","title":"Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data","created":"2024-05-23","cited_by_count":2,"area":"synth"},{"id":"2602.21218","title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors","created":"2026-01-31","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":"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":"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":"2406.09206","title":"Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models","created":"2024-06-13","cited_by_count":0,"area":"synth"},{"id":"2604.12223","title":"LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines","created":"2026-04-14","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}