{"total":38,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2512.24077","title":"LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm","created":"2025-12-30","cited_by_count":22,"area":"synth"},{"id":"2401.03038","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","created":"2024-01-05","cited_by_count":19,"area":"synth"},{"id":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"area":"synth"},{"id":"2509.07666","title":"MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval","created":"2025-09-06","cited_by_count":17,"area":"synth"},{"id":"2407.12835","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","created":"2024-07-03","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":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2409.04593","title":"Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance","created":"2024-09-06","cited_by_count":8,"area":"synth"},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2606.01314","title":"SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems","created":"2026-05-31","cited_by_count":6,"area":"synth"},{"id":"2607.01480","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models","created":"2026-07-01","cited_by_count":6,"area":"synth"},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2510.16552","title":"LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs","created":"2025-10-18","cited_by_count":5,"area":"synth"},{"id":"2412.18860","title":"Bootstrap Your Own Context Length","created":"2024-12-25","cited_by_count":4,"area":"synth"},{"id":"2503.23239","title":"Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance","created":"2025-03-29","cited_by_count":4,"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":"2508.11758","title":"Can we Evaluate RAGs with Synthetic Data?","created":"2025-08-15","cited_by_count":2,"area":"synth"},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2607.19592","title":"Knowledge-Centric Self-Improvement","created":"2026-07-21","cited_by_count":2,"area":"synth"},{"id":"2505.16102","title":"Continually Self-Improving Language Models for Bariatric Surgery Question--Answering","created":"2025-05-22","cited_by_count":1,"area":"synth"},{"id":"2512.14879","title":"Entropy-Reservoir Bregman Projection: An Information-Geometric Unification of Model Collapse","created":"2025-12-16","cited_by_count":1,"area":"synth"},{"id":"2604.10114","title":"CircuitSynth: Reliable Synthetic Data Generation","created":"2026-04-11","cited_by_count":1,"area":"synth"},{"id":"2605.17617","title":"GraphMind: From Operational Traces to Self-Evolving Workflow Automation","created":"2026-05-17","cited_by_count":1,"area":"synth"},{"id":"2605.25572","title":"PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation","created":"2026-05-25","cited_by_count":1,"area":"synth"},{"id":"2606.05513","title":"EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts","created":"2026-06-03","cited_by_count":1,"area":"synth"},{"id":"2606.28898","title":"PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs","created":"2026-06-27","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":"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":"2507.04884","title":"Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions","created":"2025-07-07","cited_by_count":0,"area":"synth"},{"id":"2510.26345","title":"MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data","created":"2025-10-30","cited_by_count":0,"area":"synth"},{"id":"2601.03792","title":"VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation","created":"2026-01-07","cited_by_count":0,"area":"synth"},{"id":"2601.05635","title":"Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs","created":"2026-01-09","cited_by_count":0,"area":"synth"},{"id":"2603.01732","title":"Bootstrapping Embeddings for Low Resource Languages","created":"2026-03-02","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":"2608.29674","title":"Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesis","created":"2026-08-30","cited_by_count":0,"area":"synth"},{"id":"2610.15908","title":"LURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges","created":"2026-10-11","cited_by_count":0,"area":"synth"}],"next_cursor":null}