{"total":75,"rows":[{"id":"2405.14333","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","created":"2024-05-23","cited_by_count":234,"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":"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":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"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":"2305.15035","title":"Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations","created":"2023-05-24","cited_by_count":42,"area":"synth"},{"id":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","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":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31,"area":"synth"},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28,"area":"synth"},{"id":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","cited_by_count":25,"area":"synth"},{"id":"2407.00116","title":"Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges","created":"2024-06-27","cited_by_count":24,"area":"synth"},{"id":"2510.12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models","created":"2025-10-14","cited_by_count":22,"area":"synth"},{"id":"2402.06806","title":"Systematic Assessment of Tabular Data Synthesis","created":"2024-02-09","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":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2406.12480","title":"The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions","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":"2505.14423","title":"Scaling Low-Resource MT via Synthetic Data Generation with LLMs","created":"2025-05-20","cited_by_count":14,"area":"synth"},{"id":"2509.21190","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","created":"2025-09-25","cited_by_count":10,"area":"synth"},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2404.14445","title":"A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models","created":"2024-04-20","cited_by_count":8,"area":"synth"},{"id":"2410.10864","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","created":"2024-10-07","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":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"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":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"area":"synth"},{"id":"2101.04758","title":"Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling","created":"2021-01-12","cited_by_count":6,"area":"synth"},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2103.07449","title":"Cooperative Self-training of Machine Reading Comprehension","created":"2021-03-12","cited_by_count":5,"area":"synth"},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"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":"2502.17957","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","created":"2025-02-25","cited_by_count":5,"area":"synth"},{"id":"2505.06297","title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","created":"2025-05-07","cited_by_count":5,"area":"synth"},{"id":"2406.18790","title":"MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data","created":"2024-06-26","cited_by_count":4,"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":"2412.00395","title":"On Foundation Models for Dynamical Systems from Purely Synthetic Data","created":"2024-11-30","cited_by_count":4,"area":"synth"},{"id":"2501.16125","title":"SampleLLM: Optimizing Tabular Data Synthesis in Recommendations","created":"2025-01-27","cited_by_count":4,"area":"synth"},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"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":"2504.18762","title":"SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum Learning","created":"2025-04-26","cited_by_count":4,"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":"2404.08078","title":"SQBC: Active Learning using LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions","created":"2024-04-11","cited_by_count":3,"area":"synth"},{"id":"2411.03356","title":"Enhancing Table Representations with LLM-powered Synthetic Data Generation","created":"2024-11-04","cited_by_count":3,"area":"synth"},{"id":"2210.07313","title":"Bootstrapping Multilingual Semantic Parsers using Large Language Models","created":"2022-10-13","cited_by_count":2,"area":"synth"},{"id":"2406.03202","title":"ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction","created":"2024-06-05","cited_by_count":2,"area":"synth"},{"id":"2409.19735","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data","created":"2024-09-29","cited_by_count":2,"area":"synth"},{"id":"2511.07044","title":"Evaluating Large Language Models for Anxiety, Depression, and Stress Detection: Insights into Prompting Strategies and Synthetic Data","created":"2025-11-10","cited_by_count":2,"area":"synth"},{"id":"2305.01547","title":"Accelerating Neural Self-Improvement via Bootstrapping","created":"2023-05-02","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":"2507.09948","title":"Iceberg: Enhancing HLS Modeling with Synthetic Data","created":"2025-07-14","cited_by_count":1,"area":"synth"},{"id":"2508.12482","title":"The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping","created":"2025-08-17","cited_by_count":1,"area":"synth"},{"id":"2509.10561","title":"AVEC: Bootstrapping Privacy for Local LLMs","created":"2025-09-10","cited_by_count":1,"area":"synth"},{"id":"2602.10531","title":"From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources","created":"2026-02-11","cited_by_count":1,"area":"synth"},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2306.10414","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","created":"2023-06-17","cited_by_count":0,"area":"synth"},{"id":"2310.19420","title":"Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings","created":"2023-10-30","cited_by_count":0,"area":"synth"},{"id":"2403.06088","title":"Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Models","created":"2024-03-10","cited_by_count":0,"area":"synth"},{"id":"2406.09206","title":"Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models","created":"2024-06-13","cited_by_count":0,"area":"synth"},{"id":"2407.06211","title":"Synthetic data: How could it be used for infectious disease research?","created":"2024-07-03","cited_by_count":0,"area":"synth"},{"id":"2410.23514","title":"Neural spell-checker: Beyond words with synthetic data generation","created":"2024-10-30","cited_by_count":0,"area":"synth"},{"id":"2505.16800","title":"Learning Beyond Limits: Multitask Learning and Synthetic Data for Low-Resource Canonical Morpheme Segmentation","created":"2025-05-22","cited_by_count":0,"area":"synth"},{"id":"2507.04884","title":"Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions","created":"2025-07-07","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":"2509.20768","title":"Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis","created":"2025-09-25","cited_by_count":0,"area":"synth"},{"id":"2512.23184","title":"From Model Choice to Model Belief: Establishing a New Measure for LLM-Based Research","created":"2025-12-29","cited_by_count":0,"area":"synth"},{"id":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","cited_by_count":0,"area":"synth"},{"id":"2602.05106","title":"Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models","created":"2026-02-04","cited_by_count":0,"area":"synth"},{"id":"2606.08471","title":"More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs","created":"2026-06-07","cited_by_count":0,"area":"synth"},{"id":"2607.13395","title":"Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models","created":"2026-07-15","cited_by_count":0,"area":"synth"},{"id":"2608.13932","title":"Post-training Quantization for Hybrid Iterative Generative Models","created":"2026-08-14","cited_by_count":0,"area":"synth"},{"id":"2608.21366","title":"Reviewing Model Collapse and Countermeasures","created":"2026-06-17","cited_by_count":0,"area":"synth"},{"id":"2609.09586","title":"Distillation of Synthetic Data for Time Series Foundation Models","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2610.12855","title":"Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization","created":"2026-10-09","cited_by_count":0,"area":"synth"}],"next_cursor":null}