{"total":26,"rows":[{"id":"2508.03613","title":"Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction","created":"2025-08-05","cited_by_count":154,"area":"synth"},{"id":"2502.11102","title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","created":"2025-02-16","cited_by_count":49,"area":"synth"},{"id":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15,"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":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9,"area":"synth"},{"id":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","cited_by_count":6,"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":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"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":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","cited_by_count":3,"area":"synth"},{"id":"2608.29966","title":"DataFoundry: Evolving Data Preparators via Recursive Self-Improvement","created":"2026-08-30","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":"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":"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":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2607.17043","title":"Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning","created":"2026-07-19","cited_by_count":1,"area":"synth"},{"id":"2506.17637","title":"Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation","created":"2025-06-21","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":"2605.30039","title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","created":"2026-05-28","cited_by_count":0,"area":"synth"},{"id":"2606.00902","title":"Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers","created":"2026-05-30","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":"2608.29144","title":"Quantifying Error Tolerance in Synthetic Data: An Atomic-level Operand vs. Operator Perturbation Study","created":"2026-08-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}