{"total":22,"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":"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":"2411.14962","title":"LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents","created":"2024-11-22","cited_by_count":12,"area":"synth"},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","cited_by_count":8,"area":"synth"},{"id":"2504.15573","title":"Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction","created":"2025-04-22","cited_by_count":8,"area":"synth"},{"id":"2412.18860","title":"Bootstrap Your Own Context Length","created":"2024-12-25","cited_by_count":4,"area":"synth"},{"id":"2505.17390","title":"Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Prompting","created":"2025-05-23","cited_by_count":4,"area":"synth"},{"id":"2505.24672","title":"TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis","created":"2025-05-30","cited_by_count":4,"area":"synth"},{"id":"2509.23041","title":"Virus Infection Attack on LLMs: Your Poisoning Can Spread \"VIA\" Synthetic Data","created":"2025-09-27","cited_by_count":4,"area":"synth"},{"id":"2412.14849","title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","created":"2024-12-19","cited_by_count":2,"area":"synth"},{"id":"2511.04478","title":"Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges","created":"2025-11-06","cited_by_count":2,"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":"2505.11533","title":"A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism","created":"2025-05-14","cited_by_count":1,"area":"synth"},{"id":"2509.15447","title":"PILOT: Steering Synthetic Data Generation with Psychological & Linguistic Output Targeting","created":"2025-09-18","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":"2604.15675","title":"C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment","created":"2026-04-17","cited_by_count":0,"area":"synth"},{"id":"2606.20400","title":"The Significance of Style Diversity in Annotation-Free Synthetic Data Generation","created":"2026-06-18","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":"2610.00814","title":"Training-Aware Target Coverage for Synthetic Data Selection","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}