{"total":71,"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":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349,"area":"synth"},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"area":"synth"},{"id":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"area":"synth"},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"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":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"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":"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":"2412.06176","title":"AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement","created":"2024-12-09","cited_by_count":35,"area":"synth"},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"id":"2310.13522","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","created":"2023-10-20","cited_by_count":26,"area":"synth"},{"id":"2501.12793","title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","created":"2025-01-22","cited_by_count":22,"area":"synth"},{"id":"2512.24077","title":"LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm","created":"2025-12-30","cited_by_count":22,"area":"synth"},{"id":"2401.03038","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","created":"2024-01-05","cited_by_count":19,"area":"synth"},{"id":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"area":"synth"},{"id":"2402.02285","title":"SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking","created":"2024-02-03","cited_by_count":17,"area":"synth"},{"id":"2409.11703","title":"Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation","created":"2024-09-18","cited_by_count":17,"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":"2407.12835","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","created":"2024-07-03","cited_by_count":15,"area":"synth"},{"id":"2304.01228","title":"Better Language Models of Code through Self-Improvement","created":"2023-04-02","cited_by_count":14,"area":"synth"},{"id":"2510.18428","title":"AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library","created":"2025-10-21","cited_by_count":14,"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":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"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":"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":"2407.05700","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","created":"2024-07-08","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":"2507.06466","title":"Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models","created":"2025-07-09","cited_by_count":6,"area":"synth"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2410.15639","title":"Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning","created":"2024-10-21","cited_by_count":4,"area":"synth"},{"id":"2412.14809","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","created":"2024-12-19","cited_by_count":4,"area":"synth"},{"id":"2503.02878","title":"Language Models can Self-Improve at State-Value Estimation for Better Search","created":"2025-03-04","cited_by_count":4,"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":"2603.15957","title":"GASP: Guided Asymmetric Self-Play For Coding LLMs","created":"2026-03-16","cited_by_count":4,"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":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2502.18517","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","created":"2025-02-23","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":"2508.09586","title":"EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making","created":"2025-08-13","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":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2405.14212","title":"Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data","created":"2024-05-23","cited_by_count":2,"area":"synth"},{"id":"2602.05810","title":"Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2603.14239","title":"QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis","created":"2026-03-15","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":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"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":"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":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.25572","title":"PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation","created":"2026-05-25","cited_by_count":1,"area":"synth"},{"id":"2607.03523","title":"Anchored Self-Play for Code Repair","created":"2026-07-03","cited_by_count":1,"area":"synth"},{"id":"2608.06474","title":"WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader","created":"2026-08-06","cited_by_count":1,"area":"synth"},{"id":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2407.10657","title":"An Empirical Study of Validating Synthetic Data for Formula Generation","created":"2024-07-15","cited_by_count":0,"area":"synth"},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2505.24165","title":"Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection","created":"2025-05-30","cited_by_count":0,"area":"synth"},{"id":"2507.15839","title":"FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs","created":"2025-07-21","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":"2507.16478","title":"ACT: Bridging the Gap in Code Translation through Synthetic Data Generation & Adaptive Training","created":"2025-07-22","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"},{"id":"2602.10171","title":"EvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems","created":"2026-02-10","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":"2606.29823","title":"Experience Graphs: The Data Foundation for Self-Improving Agents","created":"2026-06-29","cited_by_count":0,"area":"synth"},{"id":"2607.19354","title":"FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation","created":"2026-05-21","cited_by_count":0,"area":"synth"},{"id":"2609.09957","title":"Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2609.34205","title":"Learning to Optimize through Solver-Grounded Self-Play","created":"2026-09-28","cited_by_count":0,"area":"synth"}],"next_cursor":null}