{"total":14,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"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":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2407.12835","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","created":"2024-07-03","cited_by_count":15,"area":"synth"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9,"area":"synth"},{"id":"2210.16613","title":"Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers","created":"2022-10-29","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":"2510.19806","title":"The Art of Asking: Multilingual Prompt Optimization for Synthetic Data","created":"2025-10-22","cited_by_count":5,"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":"2601.04278","title":"From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning","created":"2026-01-07","cited_by_count":2,"area":"synth"},{"id":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"area":"synth"},{"id":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","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"}],"next_cursor":null}