{"total":112,"rows":[{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160,"area":null},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2410.23933","title":"Language Models can Self-Lengthen to Generate Long Texts","created":"2024-10-31","cited_by_count":24,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2502.13252","title":"Multilingual Language Model Pretraining using Machine-translated Data","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2407.18743","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models","created":"2024-07-26","cited_by_count":15,"area":null},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2410.17170","title":"Self-calibration for Language Model Quantization and Pruning","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2411.06068","title":"Zyda-2: a 5 Trillion Token High-Quality Dataset","created":"2024-11-09","cited_by_count":13,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2504.05571","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2502.04235","title":"Reformulation for Pretraining Data Augmentation","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2410.20796","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2410.22211","title":"ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2602.07824","title":"Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2408.15079","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2410.04275","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2410.05639","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2501.07314","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","created":"2025-01-13","cited_by_count":6,"area":null},{"id":"2502.14644","title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2604.13977","title":"How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2405.13010","title":"UCCIX: Irish-eXcellence Large Language Model","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2406.04638","title":"Large Language Model-guided Document Selection","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2410.23956","title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2404.10555","title":"Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2406.01981","title":"Zyda: A 1.3T Dataset for Open Language Modeling","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2409.19854","title":"The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2508.01326","title":"Large-Scale Diverse Synthesis for Mid-Training","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.18908","title":"Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2603.14420","title":"Data Darwinism Part II: DataEvolve -- AI can Autonomously Evolve Pretraining Data Curation","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2607.28109","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2411.18940","title":"Rephrasing Electronic Health Records for Pretraining Clinical Language Models","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2506.12966","title":"Assessing the Role of Data Quality in Training Bilingual Language Models","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2507.00808","title":"Multi-interaction TTS toward professional recording reproduction","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2508.01317","title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.06178","title":"Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2509.22947","title":"Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2605.17849","title":"Generating Pretraining Tokens from Organic Data for Data-Bound Scaling","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2607.25271","title":"Bridging Compute- and Data-Optimal Pretraining","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2412.04277","title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2506.01290","title":"Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.23721","title":"Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.26121","title":"GEM: Geometric Entropy Mixing for Optimal LLM Data Curation","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2607.08646","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.15267","title":"Pretraining Data Can Be Poisoned through Computational Propaganda","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.24717","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.09093","title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.17699","title":"NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2408.09585","title":"On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2507.22250","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2509.24356","title":"Beyond Repetition: Text Simplification and Curriculum Learning for Data-Constrained Pretraining","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2602.04696","title":"Beyond Learning on Molecules by Weakly Supervising on Molecules","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.22213","title":"SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.24826","title":"Synthetic Rewriting as a Quality Multiplier: Evidence from Portuguese Continued Pretraining","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.06829","title":"WRAP++: Web discoveRy Amplified Pretraining","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14969","title":"Discovering Novel LLM Experts via Task-Capability Coevolution","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.01077","title":"Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.17775","title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.22079","title":"Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.21861","title":"Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.24585","title":"From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":"100"}