{"total":21,"rows":[{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2407.01085","title":"Explaining Length Bias in LLM-Based Preference Evaluations","created":"2024-07-01","cited_by_count":49,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2505.21439","title":"Towards Better Instruction Following Retrieval Models","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2203.16682","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2210.07663","title":"Pretrained Transformers Do not Always Improve Robustness","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2603.13201","title":"Neuron-Aware Data Selection In Instruction Tuning For Large Language Models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2409.20149","title":"1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2410.14814","title":"Effects of Soft-Domain Transfer and Named Entity Information on Deception Detection","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2503.00209","title":"Autoencoder-Based Framework to Capture Vocabulary Quality in NLP","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2509.25240","title":"HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.09340","title":"Measuring Dataset Diversity from a Geometric Perspective","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2610.14031","title":"PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}