{"total":55,"rows":[{"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":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68,"area":"synth"},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43,"area":"synth"},{"id":"2305.15035","title":"Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations","created":"2023-05-24","cited_by_count":42,"area":"synth"},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36,"area":"synth"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2312.08303","title":"Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models","created":"2023-12-13","cited_by_count":21,"area":"synth"},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2402.02285","title":"SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking","created":"2024-02-03","cited_by_count":17,"area":"synth"},{"id":"2311.08921","title":"Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models","created":"2023-11-15","cited_by_count":15,"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":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"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":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","cited_by_count":10,"area":"synth"},{"id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2408.02632","title":"SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models","created":"2024-08-05","cited_by_count":9,"area":"synth"},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9,"area":"synth"},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","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":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","cited_by_count":7,"area":"synth"},{"id":"2403.11487","title":"Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis","created":"2024-03-18","cited_by_count":6,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2508.19558","title":"Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking","created":"2025-08-27","cited_by_count":4,"area":"synth"},{"id":"2411.03356","title":"Enhancing Table Representations with LLM-powered Synthetic Data Generation","created":"2024-11-04","cited_by_count":3,"area":"synth"},{"id":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","cited_by_count":3,"area":"synth"},{"id":"2511.12063","title":"TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AI","created":"2025-11-15","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":"2412.08038","title":"Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach","created":"2024-12-11","cited_by_count":2,"area":"synth"},{"id":"2503.01385","title":"Q-NL Verifier: Leveraging Synthetic Data for Robust Knowledge Graph Question Answering","created":"2025-03-03","cited_by_count":2,"area":"synth"},{"id":"2509.14624","title":"Reveal and Release: Iterative LLM Unlearning with Self-generated Data","created":"2025-09-18","cited_by_count":2,"area":"synth"},{"id":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"area":"synth"},{"id":"2605.10067","title":"Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization","created":"2026-05-11","cited_by_count":2,"area":"synth"},{"id":"2208.13376","title":"Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity","created":"2022-08-29","cited_by_count":1,"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":"2504.03877","title":"Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesis","created":"2025-04-04","cited_by_count":1,"area":"synth"},{"id":"2508.13930","title":"InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems","created":"2025-08-19","cited_by_count":1,"area":"synth"},{"id":"2510.06143","title":"RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets","created":"2025-10-07","cited_by_count":1,"area":"synth"},{"id":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","cited_by_count":1,"area":"synth"},{"id":"2602.23620","title":"Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search","created":"2026-02-27","cited_by_count":1,"area":"synth"},{"id":"2406.09206","title":"Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models","created":"2024-06-13","cited_by_count":0,"area":"synth"},{"id":"2407.11854","title":"Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection","created":"2024-07-16","cited_by_count":0,"area":"synth"},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2504.14808","title":"On Self-improving Token Embeddings","created":"2025-04-21","cited_by_count":0,"area":"synth"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","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":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2604.17738","title":"Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data","created":"2026-04-20","cited_by_count":0,"area":"synth"},{"id":"2605.05159","title":"PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation","created":"2026-05-06","cited_by_count":0,"area":"synth"},{"id":"2606.08471","title":"More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs","created":"2026-06-07","cited_by_count":0,"area":"synth"},{"id":"2607.27687","title":"Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch","created":"2026-07-30","cited_by_count":0,"area":"synth"},{"id":"2609.22149","title":"Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization","created":"2026-08-26","cited_by_count":0,"area":"synth"},{"id":"2609.37883","title":"Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping","created":"2026-09-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}