{"total":18,"rows":[{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832,"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":"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":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"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":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"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":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"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":"2406.18790","title":"MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data","created":"2024-06-26","cited_by_count":4,"area":"synth"},{"id":"2603.03796","title":"When and Where to Reset Matters for Long-Term Test-Time Adaptation","created":"2026-03-04","cited_by_count":4,"area":"synth"},{"id":"2307.04601","title":"InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval","created":"2023-07-10","cited_by_count":2,"area":"synth"},{"id":"2409.18764","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","created":"2024-09-27","cited_by_count":2,"area":"synth"},{"id":"2209.15000","title":"REST: REtrieve & Self-Train for generative action recognition","created":"2022-09-29","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":"2507.10088","title":"Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering","created":"2025-07-14","cited_by_count":0,"area":"synth"},{"id":"2608.13932","title":"Post-training Quantization for Hybrid Iterative Generative Models","created":"2026-08-14","cited_by_count":0,"area":"synth"}],"next_cursor":null}