{"total":55,"rows":[{"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":"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":"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":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"id":"2505.24726","title":"Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning","created":"2025-05-30","cited_by_count":33,"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":"2509.09396","title":"LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations","created":"2025-09-11","cited_by_count":16,"area":"synth"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","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":"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":"2410.16597","title":"Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillation","created":"2024-10-22","cited_by_count":6,"area":"synth"},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"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":"2412.19544","title":"TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data","created":"2024-12-27","cited_by_count":5,"area":"synth"},{"id":"2505.13811","title":"Context-Free Synthetic Data Mitigates Forgetting","created":"2025-05-20","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":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2406.03376","title":"Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction","created":"2024-06-05","cited_by_count":4,"area":"synth"},{"id":"2412.18860","title":"Bootstrap Your Own Context Length","created":"2024-12-25","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":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","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":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","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":"2412.18707","title":"Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data","created":"2024-12-24","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":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"area":"synth"},{"id":"2503.09029","title":"DAST: Difficulty-Aware Self-Training on Large Language Models","created":"2025-03-12","cited_by_count":3,"area":"synth"},{"id":"2504.00185","title":"Self-Evolving Visual Concept Library using Vision-Language Critics","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2505.16927","title":"Latent Principle Discovery for Language Model Self-Improvement","created":"2025-05-22","cited_by_count":2,"area":"synth"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2505.12031","title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","created":"2025-05-17","cited_by_count":1,"area":"synth"},{"id":"2508.13930","title":"InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems","created":"2025-08-19","cited_by_count":1,"area":"synth"},{"id":"2510.06143","title":"RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets","created":"2025-10-07","cited_by_count":1,"area":"synth"},{"id":"2512.05887","title":"Bootstrapping Fuzzers for Compilers of Low-Resource Language Dialects Using Language Models","created":"2025-12-05","cited_by_count":1,"area":"synth"},{"id":"2602.05145","title":"TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference","created":"2026-02-05","cited_by_count":1,"area":"synth"},{"id":"2604.11290","title":"Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation","created":"2026-04-13","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":"2606.21631","title":"CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-Training","created":"2026-06-19","cited_by_count":1,"area":"synth"},{"id":"2505.07372","title":"Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair","created":"2025-05-12","cited_by_count":0,"area":"synth"},{"id":"2509.01387","title":"ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links","created":"2025-09-01","cited_by_count":0,"area":"synth"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"},{"id":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","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":"2606.04909","title":"BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration","created":"2026-06-03","cited_by_count":0,"area":"synth"},{"id":"2609.11146","title":"The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems","created":"2026-09-10","cited_by_count":0,"area":"synth"},{"id":"2609.32546","title":"Shared Autoregressive Context Can Distort Relationships in Synthetic Data","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2609.36945","title":"Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness","created":"2026-09-29","cited_by_count":0,"area":"synth"},{"id":"2610.04646","title":"SEIS: Self-Evolving Inference Systems","created":"2026-10-03","cited_by_count":0,"area":"synth"}],"next_cursor":null}