{"total":40,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"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":"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":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"area":"synth"},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"area":"synth"},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84,"area":"synth"},{"id":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75,"area":"synth"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"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":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"area":"synth"},{"id":"2402.12368","title":"A synthetic data approach for domain generalization of NLI models","created":"2024-02-19","cited_by_count":15,"area":"synth"},{"id":"2506.05109","title":"Truly Self-Improving Agents Require Intrinsic Metacognitive Learning","created":"2025-06-05","cited_by_count":15,"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":"2502.00245","title":"Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion","created":"2025-02-01","cited_by_count":11,"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":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","cited_by_count":9,"area":"synth"},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2310.13961","title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs","created":"2023-10-21","cited_by_count":6,"area":"synth"},{"id":"2407.05474","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","created":"2024-07-07","cited_by_count":5,"area":"synth"},{"id":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2406.06056","title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","created":"2024-06-10","cited_by_count":3,"area":"synth"},{"id":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"area":"synth"},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2405.06695","title":"Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural Networks","created":"2024-05-08","cited_by_count":2,"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":"2410.10865","title":"Generating Synthetic Datasets for Few-shot Prompt Tuning","created":"2024-10-08","cited_by_count":1,"area":"synth"},{"id":"2505.06548","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","created":"2025-05-10","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":"2604.16322","title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","created":"2026-02-27","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":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2405.12579","title":"Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction","created":"2024-05-21","cited_by_count":0,"area":"synth"},{"id":"2412.16335","title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study","created":"2024-12-20","cited_by_count":0,"area":"synth"},{"id":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","cited_by_count":0,"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":"2606.03489","title":"Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs","created":"2026-06-02","cited_by_count":0,"area":"synth"},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}