{"total":17,"rows":[{"id":"2406.07217","title":"A Synthetic Dataset for Personal Attribute Inference","created":"2024-06-11","cited_by_count":36,"area":"synth"},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28,"area":"synth"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"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":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2310.01119","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","created":"2023-10-02","cited_by_count":3,"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":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","cited_by_count":3,"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":"2208.13376","title":"Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity","created":"2022-08-29","cited_by_count":1,"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":"2503.20588","title":"Synthetic Data Augmentation for Cross-domain Implicit Discourse Relation Recognition","created":"2025-03-26","cited_by_count":1,"area":"synth"},{"id":"2512.12537","title":"NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data","created":"2025-12-14","cited_by_count":1,"area":"synth"},{"id":"2607.17043","title":"Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning","created":"2026-07-19","cited_by_count":1,"area":"synth"},{"id":"2306.10414","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","created":"2023-06-17","cited_by_count":0,"area":"synth"},{"id":"2606.20400","title":"The Significance of Style Diversity in Annotation-Free Synthetic Data Generation","created":"2026-06-18","cited_by_count":0,"area":"synth"}],"next_cursor":null}