{"total":82,"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":"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":"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":"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":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"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":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"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":"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":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"id":"2410.14815","title":"Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus","created":"2024-10-18","cited_by_count":24,"area":"synth"},{"id":"2510.12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models","created":"2025-10-14","cited_by_count":22,"area":"synth"},{"id":"2402.11633","title":"Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs","created":"2024-02-18","cited_by_count":18,"area":"synth"},{"id":"2412.09243","title":"SPRec: Self-Play to Debias LLM-based Recommendation","created":"2024-12-12","cited_by_count":18,"area":"synth"},{"id":"2406.12502","title":"Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency","created":"2024-06-18","cited_by_count":16,"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":"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":"2505.19484","title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","created":"2025-05-26","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":"2506.07570","title":"OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization","created":"2025-06-09","cited_by_count":14,"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":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10,"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":"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":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","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":"2410.19290","title":"Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning","created":"2024-10-25","cited_by_count":7,"area":"synth"},{"id":"2503.12303","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","created":"2025-03-16","cited_by_count":7,"area":"synth"},{"id":"2506.15271","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","created":"2025-06-18","cited_by_count":7,"area":"synth"},{"id":"2507.04219","title":"Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs","created":"2025-07-06","cited_by_count":7,"area":"synth"},{"id":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","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":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","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":"2607.01480","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models","created":"2026-07-01","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":"2502.17957","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","created":"2025-02-25","cited_by_count":5,"area":"synth"},{"id":"2503.04959","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","created":"2025-03-06","cited_by_count":5,"area":"synth"},{"id":"2509.03937","title":"SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning","created":"2025-09-04","cited_by_count":5,"area":"synth"},{"id":"2509.25672","title":"SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation","created":"2025-09-30","cited_by_count":5,"area":"synth"},{"id":"2510.16552","title":"LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs","created":"2025-10-18","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":"2406.18078","title":"Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction","created":"2024-06-26","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":"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":"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":"2505.00031","title":"Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving","created":"2025-04-28","cited_by_count":4,"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":"2503.09029","title":"DAST: Difficulty-Aware Self-Training on Large Language Models","created":"2025-03-12","cited_by_count":3,"area":"synth"},{"id":"2507.08967","title":"Self-Improving Model Steering","created":"2025-07-11","cited_by_count":3,"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":"2601.09713","title":"LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue","created":"2025-12-24","cited_by_count":2,"area":"synth"},{"id":"2606.08092","title":"When Languages Disagree: Self-Evolving Multilingual LLM Judges","created":"2026-06-06","cited_by_count":2,"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":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","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":"2603.10823","title":"ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning","created":"2026-03-11","cited_by_count":1,"area":"synth"},{"id":"2603.25118","title":"AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization","created":"2026-03-26","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":"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":"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":"2405.12579","title":"Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction","created":"2024-05-21","cited_by_count":0,"area":"synth"},{"id":"2406.14051","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2602.05106","title":"Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models","created":"2026-02-04","cited_by_count":0,"area":"synth"},{"id":"2604.13538","title":"Synthesizing Instruction-Tuning Datasets with Contrastive Decoding","created":"2026-04-15","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":"2605.27914","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":"2606.29823","title":"Experience Graphs: The Data Foundation for Self-Improving Agents","created":"2026-06-29","cited_by_count":0,"area":"synth"},{"id":"2607.06160","title":"LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis","created":"2026-07-07","cited_by_count":0,"area":"synth"},{"id":"2607.17281","title":"AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization","created":"2026-07-19","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":"2608.30619","title":"Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text","created":"2026-08-31","cited_by_count":0,"area":"synth"},{"id":"2609.34279","title":"Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training","created":"2026-09-28","cited_by_count":0,"area":"synth"}],"next_cursor":null}