{"total":14,"rows":[{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61,"area":"synth"},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37,"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":"2505.14423","title":"Scaling Low-Resource MT via Synthetic Data Generation with LLMs","created":"2025-05-20","cited_by_count":14,"area":"synth"},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"area":"synth"},{"id":"2502.15592","title":"Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning","created":"2025-02-21","cited_by_count":8,"area":"synth"},{"id":"2412.18707","title":"Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data","created":"2024-12-24","cited_by_count":3,"area":"synth"},{"id":"2512.12537","title":"NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data","created":"2025-12-14","cited_by_count":1,"area":"synth"},{"id":"2406.14284","title":"Leveraging LLMs for Bangla Grammar Error Correction:Error Categorization, Synthetic Data, and Model Evaluation","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2510.26345","title":"MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data","created":"2025-10-30","cited_by_count":0,"area":"synth"},{"id":"2511.16132","title":"An Interpretability-Guided Framework for Responsible Synthetic Data Generation in Emotional Text","created":"2025-11-20","cited_by_count":0,"area":"synth"},{"id":"2605.05159","title":"PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation","created":"2026-05-06","cited_by_count":0,"area":"synth"},{"id":"2607.22376","title":"A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books","created":"2026-07-24","cited_by_count":0,"area":"synth"}],"next_cursor":null}