{"total":112,"rows":[{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207,"area":"synth"},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"area":"synth"},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187,"area":"synth"},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151,"area":"synth"},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128,"area":"synth"},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75,"area":"synth"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"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":"2406.07217","title":"A Synthetic Dataset for Personal Attribute Inference","created":"2024-06-11","cited_by_count":36,"area":"synth"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2509.15155","title":"Self-Improving Embodied Foundation Models","created":"2025-09-18","cited_by_count":32,"area":"synth"},{"id":"2402.03755","title":"QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model","created":"2024-02-06","cited_by_count":30,"area":"synth"},{"id":"2412.14203","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","created":"2024-12-16","cited_by_count":29,"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":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"area":"synth"},{"id":"2508.06492","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding","created":"2025-08-08","cited_by_count":20,"area":"synth"},{"id":"2502.03997","title":"CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing","created":"2025-02-06","cited_by_count":19,"area":"synth"},{"id":"2502.11741","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","created":"2025-02-17","cited_by_count":19,"area":"synth"},{"id":"2412.02674","title":"Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models","created":"2024-12-03","cited_by_count":18,"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":"2412.14352","title":"A Survey on LLM Inference-Time Self-Improvement","created":"2024-12-18","cited_by_count":17,"area":"synth"},{"id":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16,"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":"2406.11736","title":"Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models","created":"2024-06-17","cited_by_count":14,"area":"synth"},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2403.05632","title":"Can Large Language Models Play Games? A Case Study of A Self-Play Approach","created":"2024-03-08","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":"2410.19461","title":"EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data","created":"2024-10-25","cited_by_count":10,"area":"synth"},{"id":"2502.18049","title":"Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework","created":"2025-02-25","cited_by_count":10,"area":"synth"},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"area":"synth"},{"id":"2408.02632","title":"SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models","created":"2024-08-05","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":"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":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","cited_by_count":8,"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":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","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":"2508.10027","title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","created":"2025-08-08","cited_by_count":8,"area":"synth"},{"id":"2410.14655","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","created":"2024-10-18","cited_by_count":7,"area":"synth"},{"id":"2410.15828","title":"LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation","created":"2024-10-21","cited_by_count":7,"area":"synth"},{"id":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2412.15151","title":"Language Models as Continuous Self-Evolving Data Engineers","created":"2024-12-19","cited_by_count":6,"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":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2601.21343","title":"Self-Improving Pretraining: using post-trained models to pretrain better models","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"id":"2604.00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","created":"2026-04-01","cited_by_count":6,"area":"synth"},{"id":"2409.03381","title":"CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks","created":"2024-09-05","cited_by_count":5,"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":"2412.04573","title":"Give me Some Hard Questions: Synthetic Data Generation for Clinical QA","created":"2024-12-05","cited_by_count":5,"area":"synth"},{"id":"2412.20641","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","created":"2024-12-30","cited_by_count":5,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","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":"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":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2503.02152","title":"Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2504.14669","title":"Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data","created":"2025-04-20","cited_by_count":4,"area":"synth"},{"id":"2505.00031","title":"Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving","created":"2025-04-28","cited_by_count":4,"area":"synth"},{"id":"2505.13947","title":"A Probabilistic Perspective on Model Collapse","created":"2025-05-20","cited_by_count":4,"area":"synth"},{"id":"2507.18584","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","created":"2025-07-24","cited_by_count":4,"area":"synth"},{"id":"2406.06056","title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","created":"2024-06-10","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":"2506.16594","title":"A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives","created":"2025-06-19","cited_by_count":3,"area":"synth"},{"id":"2506.23520","title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","created":"2025-06-30","cited_by_count":3,"area":"synth"},{"id":"2511.20280","title":"Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement","created":"2025-11-25","cited_by_count":3,"area":"synth"},{"id":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","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":"2412.14849","title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","created":"2024-12-19","cited_by_count":2,"area":"synth"},{"id":"2507.18044","title":"Synthetic Data Generation for Phrase Break Prediction with Large Language Model","created":"2025-07-24","cited_by_count":2,"area":"synth"},{"id":"2604.14575","title":"Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidence","created":"2026-04-16","cited_by_count":2,"area":"synth"},{"id":"2605.13369","title":"Query-Conditioned Test-Time Self-Training for Large Language Models","created":"2026-05-13","cited_by_count":2,"area":"synth"},{"id":"2605.20151","title":"When Does Model Collapse Occur in Structured Interactive Learning?","created":"2026-05-19","cited_by_count":2,"area":"synth"},{"id":"2412.00657","title":"Improving Vietnamese Legal Document Retrieval using Synthetic Data","created":"2024-12-01","cited_by_count":1,"area":"synth"},{"id":"2503.13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis","created":"2025-03-18","cited_by_count":1,"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":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2509.08972","title":"ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse","created":"2025-09-10","cited_by_count":1,"area":"synth"},{"id":"2601.04875","title":"EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis","created":"2026-01-08","cited_by_count":1,"area":"synth"},{"id":"2603.07515","title":"EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification","created":"2026-03-08","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":"2606.03509","title":"EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation","created":"2026-06-02","cited_by_count":1,"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":"2504.04510","title":"Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification","created":"2025-04-06","cited_by_count":0,"area":"synth"},{"id":"2505.17671","title":"MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis","created":"2025-05-23","cited_by_count":0,"area":"synth"},{"id":"2506.12161","title":"Meta-Learning and Synthetic Data for Automated Pretraining and Finetuning","created":"2025-06-11","cited_by_count":0,"area":"synth"}],"next_cursor":"100"}