{"total":15,"rows":[{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2311.16298","title":"Influence Scores at Scale for Efficient Language Data Sampling","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2501.02432","title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2402.17227","title":"Efficient Backpropagation with Variance-Controlled Adaptive Sampling","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2411.03768","title":"A Bayesian Approach to Data Point Selection","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2312.14200","title":"Efficient Architecture Search via Bi-level Data Pruning","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2406.04892","title":"Sexism Detection on a Data Diet","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2410.05860","title":"MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2407.08887","title":"Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2503.21714","title":"As easy as PIE: understanding when pruning causes language models to disagree","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2507.04269","title":"Efficient Training of Deep Networks using Guided Spectral Data Selection: A Step Toward Learning What You Need","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2602.19789","title":"Position: Stop Preaching and Start Practising Data Frugality for Responsible Development of AI","created":"2026-02-23","cited_by_count":0,"area":null}],"next_cursor":null}