{"total":22,"rows":[{"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":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"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":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2409.16636","title":"Training Language Models to Win Debates with Self-Play Improves Judge Accuracy","created":"2024-09-25","cited_by_count":16,"area":"synth"},{"id":"2210.15206","title":"Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision","created":"2022-10-27","cited_by_count":13,"area":"synth"},{"id":"2410.02056","title":"Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data","created":"2024-10-02","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":"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":"2601.21464","title":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","created":"2026-01-29","cited_by_count":6,"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":"2608.27287","title":"Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2505.06548","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","created":"2025-05-10","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":"2606.08077","title":"Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics","created":"2026-06-06","cited_by_count":1,"area":"synth"},{"id":"2606.28898","title":"PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs","created":"2026-06-27","cited_by_count":1,"area":"synth"},{"id":"2607.13070","title":"Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale","created":"2026-07-11","cited_by_count":1,"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":"2606.03489","title":"Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs","created":"2026-06-02","cited_by_count":0,"area":"synth"}],"next_cursor":null}