{"total":43,"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":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207,"area":"synth"},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"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":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75,"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":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","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":"2310.13522","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","created":"2023-10-20","cited_by_count":26,"area":"synth"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"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":"2412.14352","title":"A Survey on LLM Inference-Time Self-Improvement","created":"2024-12-18","cited_by_count":17,"area":"synth"},{"id":"2406.18872","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games","created":"2024-06-27","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":"2402.07610","title":"Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping","created":"2024-02-12","cited_by_count":14,"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":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","cited_by_count":7,"area":"synth"},{"id":"2310.13961","title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs","created":"2023-10-21","cited_by_count":6,"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":"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":"2409.01552","title":"Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs","created":"2024-09-03","cited_by_count":5,"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":"2511.08440","title":"Coherence Mechanisms for Provable Self-Improvement","created":"2025-11-11","cited_by_count":3,"area":"synth"},{"id":"2502.04511","title":"Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis","created":"2025-02-06","cited_by_count":2,"area":"synth"},{"id":"2605.10067","title":"Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization","created":"2026-05-11","cited_by_count":2,"area":"synth"},{"id":"2603.10823","title":"ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning","created":"2026-03-11","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":"2605.23054","title":"Model Collapse as Cultural Evolution","created":"2026-05-21","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":"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":"2511.07645","title":"A Self-Improving Architecture for Dynamic Safety in Large Language Models","created":"2025-11-10","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":"2605.05546","title":"SPARK: Self-Play with Asymmetric Reward from Knowledge Graphs","created":"2026-05-07","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":"2605.27914","title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","created":"2026-05-27","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"},{"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":"2608.08471","title":"Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production","created":"2026-08-09","cited_by_count":0,"area":"synth"},{"id":"2609.36750","title":"Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving","created":"2026-09-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}