{"total":32,"rows":[{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2202.04824","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","created":"2022-02-10","cited_by_count":30,"area":null},{"id":"2410.11303","title":"TSDS: Data Selection for Task-Specific Model Finetuning","created":"2024-10-15","cited_by_count":28,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2209.14389","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2202.00911","title":"Active Multi-Task Representation Learning","created":"2022-02-02","cited_by_count":14,"area":null},{"id":"2306.11670","title":"GIO: Gradient Information Optimization for Training Dataset Selection","created":"2023-06-20","cited_by_count":13,"area":null},{"id":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2211.00430","title":"VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding","created":"2022-11-01","cited_by_count":12,"area":null},{"id":"2305.12816","title":"Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2401.14624","title":"Unearthing Large Scale Domain-Specific Knowledge from Public Corpora","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2208.12995","title":"Domain-Specific NER via Retrieving Correlated Samples","created":"2022-08-27","cited_by_count":11,"area":null},{"id":"2306.02556","title":"Improved Active Multi-Task Representation Learning via Lasso","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2410.17018","title":"Exploring Forgetting in Large Language Model Pre-Training","created":"2024-10-22","cited_by_count":9,"area":null},{"id":"2210.04382","title":"Parameter-Efficient Tuning with Special Token Adaptation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2311.01786","title":"TCM-GPT: Efficient Pre-training of Large Language Models for Domain Adaptation in Traditional Chinese Medicine","created":"2023-11-03","cited_by_count":7,"area":null},{"id":"2210.06656","title":"Knowledge-grounded Dialog State Tracking","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2309.04862","title":"Distributional Data Augmentation Methods for Low Resource Language","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2306.08942","title":"Active Representation Learning for General Task Space with Applications in Robotics","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2401.05883","title":"Generative Deduplication For Socia Media Data Selection","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2502.19513","title":"Mixtraining: A Better Trade-Off Between Compute and Performance","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2210.12022","title":"Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2311.09732","title":"Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2508.03175","title":"Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2512.22675","title":"Beyond Centralization: Provable Communication Efficient Decentralized Multi-Task Learning","created":"2025-12-27","cited_by_count":0,"area":null}],"next_cursor":null}