{"total":16,"rows":[{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2409.01577","title":"EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding","created":"2024-09-03","cited_by_count":34,"area":"synth"},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2412.14203","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","created":"2024-12-16","cited_by_count":29,"area":"synth"},{"id":"2505.17231","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","created":"2025-05-22","cited_by_count":12,"area":"synth"},{"id":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"area":"synth"},{"id":"2510.03687","title":"MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction","created":"2025-10-04","cited_by_count":8,"area":"synth"},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2412.20641","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","created":"2024-12-30","cited_by_count":5,"area":"synth"},{"id":"2406.03376","title":"Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction","created":"2024-06-05","cited_by_count":4,"area":"synth"},{"id":"2503.15055","title":"ELTEX: A Framework for Domain-Driven Synthetic Data Generation","created":"2025-03-19","cited_by_count":2,"area":"synth"},{"id":"2605.20151","title":"When Does Model Collapse Occur in Structured Interactive Learning?","created":"2026-05-19","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":"2604.04274","title":"InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI","created":"2026-04-05","cited_by_count":0,"area":"synth"},{"id":"2605.30039","title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","created":"2026-05-28","cited_by_count":0,"area":"synth"},{"id":"2610.01493","title":"No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse","created":"2026-10-01","cited_by_count":0,"area":"synth"}],"next_cursor":null}