{"total":76,"rows":[{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84,"area":"synth"},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68,"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":"2502.11102","title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","created":"2025-02-16","cited_by_count":49,"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":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","cited_by_count":33,"area":"synth"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2408.02927","title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","created":"2024-08-06","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":"2406.05892","title":"Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models","created":"2024-06-09","cited_by_count":14,"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":"2407.17493","title":"Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling","created":"2024-07-04","cited_by_count":12,"area":"synth"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2310.00646","title":"Source Attribution for Large Language Model-Generated Data","created":"2023-10-01","cited_by_count":11,"area":"synth"},{"id":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9,"area":"synth"},{"id":"2502.04419","title":"Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","created":"2025-02-06","cited_by_count":9,"area":"synth"},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","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":"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":"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":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","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":"2404.01720","title":"Self-Improvement Programming for Temporal Knowledge Graph Question Answering","created":"2024-04-02","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":"2505.13811","title":"Context-Free Synthetic Data Mitigates Forgetting","created":"2025-05-20","cited_by_count":5,"area":"synth"},{"id":"2510.04399","title":"On The Statistical Limits of Self-Improving Agents","created":"2025-10-05","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":"2406.18790","title":"MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data","created":"2024-06-26","cited_by_count":4,"area":"synth"},{"id":"2408.16310","title":"Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning","created":"2024-08-29","cited_by_count":4,"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":"2503.02152","title":"Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis","created":"2025-03-04","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":"2504.18762","title":"SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum Learning","created":"2025-04-26","cited_by_count":4,"area":"synth"},{"id":"2505.17410","title":"LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context","created":"2025-05-23","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":"2403.03690","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","created":"2024-03-06","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":"2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","created":"2025-10-08","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":"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":"2311.06364","title":"Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach","created":"2023-11-10","cited_by_count":1,"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":"2410.10865","title":"Generating Synthetic Datasets for Few-shot Prompt Tuning","created":"2024-10-08","cited_by_count":1,"area":"synth"},{"id":"2503.20715","title":"From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models","created":"2025-03-26","cited_by_count":1,"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":"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":"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":"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":"2609.04511","title":"LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs","created":"2026-09-03","cited_by_count":1,"area":"synth"},{"id":"2311.03243","title":"Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM","created":"2023-11-06","cited_by_count":0,"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":"2406.14284","title":"Leveraging LLMs for Bangla Grammar Error Correction:Error Categorization, Synthetic Data, and Model Evaluation","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2407.10657","title":"An Empirical Study of Validating Synthetic Data for Formula Generation","created":"2024-07-15","cited_by_count":0,"area":"synth"},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2502.10263","title":"Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers","created":"2025-02-14","cited_by_count":0,"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":"2506.12161","title":"Meta-Learning and Synthetic Data for Automated Pretraining and Finetuning","created":"2025-06-11","cited_by_count":0,"area":"synth"},{"id":"2506.17637","title":"Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation","created":"2025-06-21","cited_by_count":0,"area":"synth"},{"id":"2507.16478","title":"ACT: Bridging the Gap in Code Translation through Synthetic Data Generation & Adaptive Training","created":"2025-07-22","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":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","cited_by_count":0,"area":"synth"},{"id":"2603.01732","title":"Bootstrapping Embeddings for Low Resource Languages","created":"2026-03-02","cited_by_count":0,"area":"synth"},{"id":"2603.16044","title":"Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation","created":"2026-03-17","cited_by_count":0,"area":"synth"},{"id":"2604.17738","title":"Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data","created":"2026-04-20","cited_by_count":0,"area":"synth"},{"id":"2605.09855","title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2609.32984","title":"ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2609.38721","title":"UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2609.39679","title":"SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.01493","title":"No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse","created":"2026-10-01","cited_by_count":0,"area":"synth"},{"id":"2610.03476","title":"MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation","created":"2026-10-02","cited_by_count":0,"area":"synth"},{"id":"2610.12855","title":"Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization","created":"2026-10-09","cited_by_count":0,"area":"synth"}],"next_cursor":null}