{"total":21,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"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":"2406.01457","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":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","cited_by_count":10,"area":"synth"},{"id":"2604.09377","title":"Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios","created":"2026-04-10","cited_by_count":10,"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":"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":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"area":"synth"},{"id":"2405.09997","title":"Generative Design through Quality-Diversity Data Synthesis and Language Models","created":"2024-05-16","cited_by_count":3,"area":"synth"},{"id":"2501.01793","title":"Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation","created":"2025-01-03","cited_by_count":3,"area":"synth"},{"id":"2511.08440","title":"Coherence Mechanisms for Provable Self-Improvement","created":"2025-11-11","cited_by_count":3,"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":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"area":"synth"},{"id":"2305.18915","title":"Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures","created":"2023-05-30","cited_by_count":0,"area":"synth"},{"id":"2507.15839","title":"FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs","created":"2025-07-21","cited_by_count":0,"area":"synth"},{"id":"2510.01229","title":"Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based Supervision","created":"2025-09-23","cited_by_count":0,"area":"synth"},{"id":"2609.37883","title":"Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping","created":"2026-09-29","cited_by_count":0,"area":"synth"},{"id":"2609.39447","title":"Synthetic Data Characterization via Training Dynamics","created":"2026-09-30","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}