{"total":25,"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":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"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":"2402.11633","title":"Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs","created":"2024-02-18","cited_by_count":18,"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":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2502.15592","title":"Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning","created":"2025-02-21","cited_by_count":8,"area":"synth"},{"id":"2410.14655","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","created":"2024-10-18","cited_by_count":7,"area":"synth"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","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":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"area":"synth"},{"id":"2603.12932","title":"DS$^2$-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning","created":"2026-03-13","cited_by_count":4,"area":"synth"},{"id":"2411.15484","title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","created":"2024-11-23","cited_by_count":3,"area":"synth"},{"id":"2502.04511","title":"Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis","created":"2025-02-06","cited_by_count":2,"area":"synth"},{"id":"2601.09713","title":"LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue","created":"2025-12-24","cited_by_count":2,"area":"synth"},{"id":"2608.26958","title":"Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2608.29966","title":"DataFoundry: Evolving Data Preparators via Recursive Self-Improvement","created":"2026-08-30","cited_by_count":2,"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":"2602.01357","title":"Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning","created":"2026-02-01","cited_by_count":1,"area":"synth"},{"id":"2603.09231","title":"Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2604.20933","title":"IRIS: Interpolative R\\'enyi Iterative Self-play for Large Language Model Fine-Tuning","created":"2026-04-22","cited_by_count":0,"area":"synth"},{"id":"2605.09922","title":"Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2605.30039","title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","created":"2026-05-28","cited_by_count":0,"area":"synth"}],"next_cursor":null}