{"total":18,"rows":[{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61,"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":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"id":"2603.02218","title":"Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain","created":"2026-02-10","cited_by_count":17,"area":"synth"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2407.05700","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","created":"2024-07-08","cited_by_count":8,"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":"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":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2603.24202","title":"A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula","created":"2026-03-25","cited_by_count":3,"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":"2505.23177","title":"Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification","created":"2025-05-29","cited_by_count":1,"area":"synth"},{"id":"2512.00380","title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","created":"2025-11-29","cited_by_count":1,"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":"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":"2601.05635","title":"Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs","created":"2026-01-09","cited_by_count":0,"area":"synth"},{"id":"2606.03489","title":"Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs","created":"2026-06-02","cited_by_count":0,"area":"synth"}],"next_cursor":null}