{"total":14,"rows":[{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"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":"2406.12502","title":"Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency","created":"2024-06-18","cited_by_count":16,"area":"synth"},{"id":"2311.07070","title":"Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations","created":"2023-11-13","cited_by_count":12,"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":"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":"2410.02992","title":"Learning to Better Search with Language Models via Guided Reinforced Self-Training","created":"2024-10-03","cited_by_count":5,"area":"synth"},{"id":"2503.04959","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","created":"2025-03-06","cited_by_count":5,"area":"synth"},{"id":"2306.06347","title":"DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies","created":"2023-06-10","cited_by_count":3,"area":"synth"},{"id":"2403.00338","title":"Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models","created":"2024-03-01","cited_by_count":3,"area":"synth"},{"id":"2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","created":"2025-10-08","cited_by_count":2,"area":"synth"},{"id":"2311.03243","title":"Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM","created":"2023-11-06","cited_by_count":0,"area":"synth"},{"id":"2507.15889","title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing","created":"2025-07-20","cited_by_count":0,"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"}],"next_cursor":null}