{"total":123,"rows":[{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84,"area":"synth"},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65,"area":"synth"},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"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":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"id":"2509.15155","title":"Self-Improving Embodied Foundation Models","created":"2025-09-18","cited_by_count":32,"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":"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":"2501.12793","title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","created":"2025-01-22","cited_by_count":22,"area":"synth"},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"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":"2412.09243","title":"SPRec: Self-Play to Debias LLM-based Recommendation","created":"2024-12-12","cited_by_count":18,"area":"synth"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","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":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","cited_by_count":14,"area":"synth"},{"id":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"area":"synth"},{"id":"2501.01384","title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","created":"2025-01-02","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":"2502.15592","title":"Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning","created":"2025-02-21","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":"2508.10027","title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","created":"2025-08-08","cited_by_count":8,"area":"synth"},{"id":"2410.08942","title":"Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2410.15828","title":"LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation","created":"2024-10-21","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":"2412.07030","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","created":"2024-12-09","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":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","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":"2508.06635","title":"Valid Inference with Imperfect Synthetic Data","created":"2025-08-08","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":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"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":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","cited_by_count":6,"area":"synth"},{"id":"2505.15392","title":"Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations","created":"2025-05-21","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":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","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":"2604.00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","created":"2026-04-01","cited_by_count":6,"area":"synth"},{"id":"2410.02992","title":"Learning to Better Search with Language Models via Guided Reinforced Self-Training","created":"2024-10-03","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":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"area":"synth"},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2510.09051","title":"Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation","created":"2025-10-10","cited_by_count":5,"area":"synth"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"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":"2412.18860","title":"Bootstrap Your Own Context Length","created":"2024-12-25","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":"2503.23239","title":"Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance","created":"2025-03-29","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":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2507.18584","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","created":"2025-07-24","cited_by_count":4,"area":"synth"},{"id":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","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":"2509.15568","title":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","created":"2025-09-19","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":"2603.24202","title":"A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula","created":"2026-03-25","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":"2409.19735","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data","created":"2024-09-29","cited_by_count":2,"area":"synth"},{"id":"2412.14849","title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","created":"2024-12-19","cited_by_count":2,"area":"synth"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2504.00185","title":"Self-Evolving Visual Concept Library using Vision-Language Critics","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2504.05317","title":"On Synthesizing Data for Context Attribution in Question Answering","created":"2025-02-21","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":"2511.07044","title":"Evaluating Large Language Models for Anxiety, Depression, and Stress Detection: Insights into Prompting Strategies and Synthetic Data","created":"2025-11-10","cited_by_count":2,"area":"synth"},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","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":"2602.21218","title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors","created":"2026-01-31","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":"2410.06845","title":"MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders","created":"2024-10-09","cited_by_count":1,"area":"synth"},{"id":"2501.07959","title":"Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning","created":"2025-01-14","cited_by_count":1,"area":"synth"},{"id":"2503.20588","title":"Synthetic Data Augmentation for Cross-domain Implicit Discourse Relation Recognition","created":"2025-03-26","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":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2508.13930","title":"InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems","created":"2025-08-19","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":"2601.04875","title":"EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis","created":"2026-01-08","cited_by_count":1,"area":"synth"},{"id":"2602.05145","title":"TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference","created":"2026-02-05","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":"2606.28898","title":"PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs","created":"2026-06-27","cited_by_count":1,"area":"synth"},{"id":"2607.11883","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":"2505.17671","title":"MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis","created":"2025-05-23","cited_by_count":0,"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":"2506.12161","title":"Meta-Learning and Synthetic Data for Automated Pretraining and Finetuning","created":"2025-06-11","cited_by_count":0,"area":"synth"},{"id":"2507.04884","title":"Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions","created":"2025-07-07","cited_by_count":0,"area":"synth"},{"id":"2508.19807","title":"Bootstrapping Learned Cost Models with Synthetic SQL Queries","created":"2025-08-27","cited_by_count":0,"area":"synth"},{"id":"2509.23594","title":"StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data","created":"2025-09-28","cited_by_count":0,"area":"synth"},{"id":"2510.26345","title":"MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data","created":"2025-10-30","cited_by_count":0,"area":"synth"},{"id":"2511.01183","title":"QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code","created":"2025-11-03","cited_by_count":0,"area":"synth"},{"id":"2511.07982","title":"NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation","created":"2025-11-11","cited_by_count":0,"area":"synth"},{"id":"2511.09539","title":"SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim Verification","created":"2025-11-12","cited_by_count":0,"area":"synth"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"}],"next_cursor":"100"}