{"total":21,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"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":"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":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"id":"2502.11741","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","created":"2025-02-17","cited_by_count":19,"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":"2404.12404","title":"EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models","created":"2024-04-15","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":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"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":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","cited_by_count":3,"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":"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":"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":"2511.17630","title":"Can we use LLMs to bootstrap reinforcement learning? -- A case study in digital health behavior change","created":"2025-11-19","cited_by_count":0,"area":"synth"},{"id":"2603.04423","title":"Generating Realistic, Protocol-Compliant Maritime Radio Dialogues using Self-Instruct and Low-Rank Adaptation","created":"2026-02-16","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":"2610.04912","title":"Static Bootstrap Placement for Encrypted Language Model Decoding","created":"2026-10-04","cited_by_count":0,"area":"synth"}],"next_cursor":null}