{"total":20,"rows":[{"id":"2305.10703","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"area":null},{"id":"2310.14563","title":"NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation","created":"2023-10-23","cited_by_count":24,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2602.18462","title":"Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents","created":"2026-02-06","cited_by_count":10,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2309.06503","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2310.06111","title":"BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2406.10573","title":"Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions","created":"2024-06-15","cited_by_count":4,"area":null},{"id":"2506.00955","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2405.20787","title":"PGA-SciRE: Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2411.14896","title":"Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2508.05283","title":"Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2508.09515","title":"LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2503.05047","title":"Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2508.09516","title":"Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2410.12622","title":"From Measurement Instruments to Data: Leveraging Theory-Driven Synthetic Training Data for Classifying Social Constructs","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2510.27512","title":"When Distributions Shifts: Causal Generalization for Low-Resource Languages","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.18854","title":"Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2605.24296","title":"When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":null}