{"total":47,"rows":[{"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":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"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":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68,"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":"2203.09101","title":"RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction","created":"2022-03-17","cited_by_count":60,"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":"2505.24726","title":"Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning","created":"2025-05-30","cited_by_count":33,"area":"synth"},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26,"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":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","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":"2307.03692","title":"Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning","created":"2023-07-05","cited_by_count":13,"area":"synth"},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2110.06274","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","created":"2021-10-12","cited_by_count":9,"area":"synth"},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","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":"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":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","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":"2607.01480","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models","created":"2026-07-01","cited_by_count":6,"area":"synth"},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","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":"2506.00649","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction","created":"2025-05-31","cited_by_count":4,"area":"synth"},{"id":"2306.03315","title":"Few Shot Rationale Generation using Self-Training with Dual Teachers","created":"2023-06-05","cited_by_count":3,"area":"synth"},{"id":"2310.01119","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","created":"2023-10-02","cited_by_count":3,"area":"synth"},{"id":"2511.08440","title":"Coherence Mechanisms for Provable Self-Improvement","created":"2025-11-11","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":"2401.00575","title":"Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets","created":"2023-12-31","cited_by_count":2,"area":"synth"},{"id":"2506.19952","title":"CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation","created":"2025-06-24","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":"2605.20151","title":"When Does Model Collapse Occur in Structured Interactive Learning?","created":"2026-05-19","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":"2305.01547","title":"Accelerating Neural Self-Improvement via Bootstrapping","created":"2023-05-02","cited_by_count":1,"area":"synth"},{"id":"2512.14879","title":"Entropy-Reservoir Bregman Projection: An Information-Geometric Unification of Model Collapse","created":"2025-12-16","cited_by_count":1,"area":"synth"},{"id":"2605.07977","title":"Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2607.11883","title":"Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data","created":"2026-07-13","cited_by_count":1,"area":"synth"},{"id":"2601.03792","title":"VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation","created":"2026-01-07","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":"2605.16379","title":"An Information-Theoretic Criterion for Efficient Data Synthesis","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2606.04238","title":"Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data","created":"2026-06-02","cited_by_count":0,"area":"synth"},{"id":"2607.09751","title":"Task-Conditioned Synthetic Data Generation for Improving Machine Learning Performance in Agricultural Prediction Tasks","created":"2026-07-04","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":"2610.10832","title":"MotherTree: Meta-learning on synthetic data improves decision tree training","created":"2026-10-07","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}