{"total":19,"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":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"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":"2502.11741","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","created":"2025-02-17","cited_by_count":19,"area":"synth"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"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":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2507.18584","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","created":"2025-07-24","cited_by_count":4,"area":"synth"},{"id":"2503.09029","title":"DAST: Difficulty-Aware Self-Training on Large Language Models","created":"2025-03-12","cited_by_count":3,"area":"synth"},{"id":"2601.11776","title":"Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models","created":"2026-01-16","cited_by_count":1,"area":"synth"},{"id":"2604.21916","title":"MathDuels: A Self-Play Benchmark That Grows","created":"2026-04-23","cited_by_count":1,"area":"synth"},{"id":"2505.24165","title":"Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection","created":"2025-05-30","cited_by_count":0,"area":"synth"},{"id":"2610.08093","title":"SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis","created":"2026-10-06","cited_by_count":0,"area":"synth"}],"next_cursor":null}