{"total":94,"rows":[{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090,"area":"synth"},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832,"area":"synth"},{"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":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"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":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"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":"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":"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":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"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":"2310.13522","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","created":"2023-10-20","cited_by_count":26,"area":"synth"},{"id":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"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":"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":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2506.05109","title":"Truly Self-Improving Agents Require Intrinsic Metacognitive Learning","created":"2025-06-05","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":"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":"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":"2505.19475","title":"Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection","created":"2025-05-26","cited_by_count":13,"area":"synth"},{"id":"2408.09849","title":"Importance Weighting Can Help Large Language Models Self-Improve","created":"2024-08-19","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":"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":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","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":"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":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","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":"2507.00075","title":"Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap","created":"2025-06-29","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":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","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":"2510.09051","title":"Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation","created":"2025-10-10","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":"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":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2603.12932","title":"DS$^2$-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning","created":"2026-03-13","cited_by_count":4,"area":"synth"},{"id":"2606.07856","title":"Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@$K$ Crossover on a Free-Verifier Domain","created":"2026-06-05","cited_by_count":4,"area":"synth"},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","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":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","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":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2606.07001","title":"DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-Evolving","created":"2026-06-05","cited_by_count":3,"area":"synth"},{"id":"2407.03942","title":"Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data","created":"2024-07-04","cited_by_count":2,"area":"synth"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2509.14624","title":"Reveal and Release: Iterative LLM Unlearning with Self-generated Data","created":"2025-09-18","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":"2601.04278","title":"From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning","created":"2026-01-07","cited_by_count":2,"area":"synth"},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","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":"2605.13369","title":"Query-Conditioned Test-Time Self-Training for Large Language Models","created":"2026-05-13","cited_by_count":2,"area":"synth"},{"id":"2605.26132","title":"Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline","created":"2026-05-20","cited_by_count":2,"area":"synth"},{"id":"2608.02139","title":"Self-Improving Large Language Models via Progressive Experience Evolution","created":"2026-08-03","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":"2608.26958","title":"Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable","created":"2026-08-27","cited_by_count":2,"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":"2601.11776","title":"Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models","created":"2026-01-16","cited_by_count":1,"area":"synth"},{"id":"2602.01357","title":"Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning","created":"2026-02-01","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":"2604.21916","title":"MathDuels: A Self-Play Benchmark That Grows","created":"2026-04-23","cited_by_count":1,"area":"synth"},{"id":"2604.24819","title":"Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora","created":"2026-04-27","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":"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":"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":"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":"2510.11842","title":"Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities","created":"2025-10-13","cited_by_count":0,"area":"synth"},{"id":"2601.00885","title":"Counterfactual Self-Questioning for Stable Policy Optimization in Language Models","created":"2025-12-31","cited_by_count":0,"area":"synth"},{"id":"2602.10014","title":"A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula","created":"2026-02-10","cited_by_count":0,"area":"synth"},{"id":"2603.20441","title":"A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement","created":"2026-03-20","cited_by_count":0,"area":"synth"},{"id":"2604.20933","title":"IRIS: Interpolative R\\'enyi Iterative Self-play for Large Language Model Fine-Tuning","created":"2026-04-22","cited_by_count":0,"area":"synth"},{"id":"2605.09922","title":"Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs","created":"2026-05-11","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":"2606.08471","title":"More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs","created":"2026-06-07","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":"2608.21366","title":"Reviewing Model Collapse and Countermeasures","created":"2026-06-17","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"},{"id":"2608.30619","title":"Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text","created":"2026-08-31","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"},{"id":"2609.34279","title":"Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2610.00814","title":"Training-Aware Target Coverage for Synthetic Data Selection","created":"2026-09-30","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"},{"id":"2610.09239","title":"The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules","created":"2026-10-07","cited_by_count":0,"area":"synth"}],"next_cursor":null}