{"total":92,"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":"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":"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":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57,"area":"synth"},{"id":"2311.08182","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","created":"2023-11-14","cited_by_count":52,"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":"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":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"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":"2312.08303","title":"Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models","created":"2023-12-13","cited_by_count":21,"area":"synth"},{"id":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"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":"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":"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":"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":"2602.12612","title":"Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback","created":"2026-02-13","cited_by_count":10,"area":"synth"},{"id":"2605.19576","title":"Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries","created":"2026-05-19","cited_by_count":10,"area":"synth"},{"id":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"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":"2410.24105","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","created":"2024-10-31","cited_by_count":9,"area":"synth"},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","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":"2604.27488","title":"Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO","created":"2026-04-30","cited_by_count":8,"area":"synth"},{"id":"2404.02422","title":"Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data","created":"2024-04-03","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":"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":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","cited_by_count":6,"area":"synth"},{"id":"2507.06466","title":"Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models","created":"2025-07-09","cited_by_count":6,"area":"synth"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","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":"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":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"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":"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":"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":"2606.27226","title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","created":"2026-06-25","cited_by_count":5,"area":"synth"},{"id":"2608.29856","title":"GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation","created":"2026-08-30","cited_by_count":5,"area":"synth"},{"id":"2608.31100","title":"S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?","created":"2026-08-31","cited_by_count":5,"area":"synth"},{"id":"2506.08646","title":"TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning","created":"2025-06-10","cited_by_count":4,"area":"synth"},{"id":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","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":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"area":"synth"},{"id":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","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":"2405.14212","title":"Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data","created":"2024-05-23","cited_by_count":2,"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":"2505.08905","title":"Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora","created":"2025-05-13","cited_by_count":2,"area":"synth"},{"id":"2505.16065","title":"Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation","created":"2025-05-21","cited_by_count":2,"area":"synth"},{"id":"2505.16927","title":"Latent Principle Discovery for Language Model Self-Improvement","created":"2025-05-22","cited_by_count":2,"area":"synth"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2511.04478","title":"Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges","created":"2025-11-06","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":"2601.14160","title":"Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law","created":"2026-01-20","cited_by_count":2,"area":"synth"},{"id":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","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":"2606.28438","title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","created":"2026-06-26","cited_by_count":2,"area":"synth"},{"id":"2405.19773","title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","created":"2024-05-30","cited_by_count":1,"area":"synth"},{"id":"2505.11533","title":"A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism","created":"2025-05-14","cited_by_count":1,"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":"2604.21916","title":"MathDuels: A Self-Play Benchmark That Grows","created":"2026-04-23","cited_by_count":1,"area":"synth"},{"id":"2606.01148","title":"Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales","created":"2026-05-31","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":"2606.13629","title":"Valid Inference with Synthetic Data via Task Exchangeability","created":"2026-06-11","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":"2608.26159","title":"Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation","created":"2026-07-07","cited_by_count":1,"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":"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":"2601.03792","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":"2601.11792","title":"A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation","created":"2026-01-16","cited_by_count":0,"area":"synth"},{"id":"2601.18253","title":"BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation","created":"2026-01-26","cited_by_count":0,"area":"synth"},{"id":"2603.09231","title":"Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2603.09403","title":"LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2604.04274","title":"InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI","created":"2026-04-05","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":"2605.02277","title":"CECOR: Correction-oriented synthetic data construction for factual error correction","created":"2026-05-04","cited_by_count":0,"area":"synth"},{"id":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","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":"2605.28882","title":"GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human","created":"2026-05-26","cited_by_count":0,"area":"synth"},{"id":"2606.04909","title":"BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration","created":"2026-06-03","cited_by_count":0,"area":"synth"},{"id":"2607.18358","title":"A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification","created":"2026-07-20","cited_by_count":0,"area":"synth"},{"id":"2607.27687","title":"Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch","created":"2026-07-30","cited_by_count":0,"area":"synth"},{"id":"2608.17468","title":"SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution","created":"2026-08-18","cited_by_count":0,"area":"synth"}],"next_cursor":null}