{"total":20,"rows":[{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"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":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2505.20416","title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","created":"2025-05-26","cited_by_count":8,"area":"synth"},{"id":"2412.07030","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","created":"2024-12-09","cited_by_count":7,"area":"synth"},{"id":"2505.00022","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","created":"2025-04-24","cited_by_count":6,"area":"synth"},{"id":"2505.00979","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models","created":"2025-05-02","cited_by_count":4,"area":"synth"},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2601.05635","title":"Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs","created":"2026-01-09","cited_by_count":0,"area":"synth"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2607.27379","title":"HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs","created":"2026-07-29","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"},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}