{"total":22,"rows":[{"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":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2203.09101","title":"RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction","created":"2022-03-17","cited_by_count":60,"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":"2304.11872","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","created":"2023-04-24","cited_by_count":12,"area":"synth"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2502.18049","title":"Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework","created":"2025-02-25","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":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","cited_by_count":8,"area":"synth"},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","cited_by_count":8,"area":"synth"},{"id":"2403.13804","title":"Learning from Synthetic Data for Visual Grounding","created":"2024-03-20","cited_by_count":4,"area":"synth"},{"id":"2509.23041","title":"Virus Infection Attack on LLMs: Your Poisoning Can Spread \"VIA\" Synthetic Data","created":"2025-09-27","cited_by_count":4,"area":"synth"},{"id":"2302.06860","title":"BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction","created":"2023-02-14","cited_by_count":3,"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":"2311.06364","title":"Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach","created":"2023-11-10","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":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2511.16132","title":"An Interpretability-Guided Framework for Responsible Synthetic Data Generation in Emotional Text","created":"2025-11-20","cited_by_count":0,"area":"synth"},{"id":"2609.17549","title":"Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues","created":"2026-07-15","cited_by_count":0,"area":"synth"},{"id":"2609.39447","title":"Synthetic Data Characterization via Training Dynamics","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}