{"total":27,"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":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","cited_by_count":13,"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":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","cited_by_count":8,"area":"synth"},{"id":"2405.11162","title":"LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs","created":"2024-05-18","cited_by_count":7,"area":"synth"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","cited_by_count":7,"area":"synth"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2509.03937","title":"SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning","created":"2025-09-04","cited_by_count":5,"area":"synth"},{"id":"2508.19558","title":"Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking","created":"2025-08-27","cited_by_count":4,"area":"synth"},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2504.09643","title":"Iterative Self-Training for Code Generation via Reinforced Re-Ranking","created":"2025-04-13","cited_by_count":3,"area":"synth"},{"id":"2509.18719","title":"LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection","created":"2025-09-23","cited_by_count":3,"area":"synth"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2606.28438","title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","created":"2026-06-26","cited_by_count":2,"area":"synth"},{"id":"2602.20799","title":"Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphs","created":"2026-02-24","cited_by_count":1,"area":"synth"},{"id":"2603.25118","title":"AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization","created":"2026-03-26","cited_by_count":1,"area":"synth"},{"id":"2604.16322","title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","created":"2026-02-27","cited_by_count":1,"area":"synth"},{"id":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2509.07858","title":"SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs","created":"2025-09-09","cited_by_count":0,"area":"synth"},{"id":"2604.18639","title":"Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning","created":"2026-04-19","cited_by_count":0,"area":"synth"},{"id":"2606.29155","title":"OASIF: An Efficient Obfuscation-Aware Self-Improving Framework for LLM-Based Assembly Code Instruction Following and Comprehension","created":"2026-06-28","cited_by_count":0,"area":"synth"},{"id":"2607.17139","title":"SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training","created":"2026-07-19","cited_by_count":0,"area":"synth"}],"next_cursor":null}