{"total":17,"rows":[{"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":"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":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"id":"2406.07217","title":"A Synthetic Dataset for Personal Attribute Inference","created":"2024-06-11","cited_by_count":36,"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":"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":"2407.05700","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","created":"2024-07-08","cited_by_count":8,"area":"synth"},{"id":"2406.03376","title":"Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction","created":"2024-06-05","cited_by_count":4,"area":"synth"},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2511.20280","title":"Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement","created":"2025-11-25","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":"2503.13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis","created":"2025-03-18","cited_by_count":1,"area":"synth"},{"id":"2510.06695","title":"Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks","created":"2025-10-08","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":"2605.14062","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":"2606.29155","title":"OASIF: An Efficient Obfuscation-Aware Self-Improving Framework for LLM-Based Assembly Code Instruction Following and Comprehension","created":"2026-06-28","cited_by_count":0,"area":"synth"},{"id":"2607.17281","title":"AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization","created":"2026-07-19","cited_by_count":0,"area":"synth"}],"next_cursor":null}