{"total":18,"rows":[{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"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":"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":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2506.15271","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","created":"2025-06-18","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":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2604.00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","created":"2026-04-01","cited_by_count":6,"area":"synth"},{"id":"2412.18860","title":"Bootstrap Your Own Context Length","created":"2024-12-25","cited_by_count":4,"area":"synth"},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2506.00649","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction","created":"2025-05-31","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":"2607.11883","title":"Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data","created":"2026-07-13","cited_by_count":1,"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":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","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}