{"total":55,"rows":[{"id":"2504.13161","title":"Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training","created":"2025-04-17","cited_by_count":66,"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":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","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":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2506.12044","title":"Why Do Some Inputs Break Low-Bit LLM Quantization?","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2510.25771","title":"Gaperon: A Peppered English-French Generative Language Model Suite","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2506.14111","title":"Essential-Web v1.0: 24T tokens of organized web data","created":"2025-06-17","cited_by_count":8,"area":null},{"id":"2511.23119","title":"Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2508.17677","title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training","created":"2025-08-25","cited_by_count":6,"area":null},{"id":"2512.24265","title":"Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning","created":"2025-12-30","cited_by_count":5,"area":null},{"id":"2502.16802","title":"Topic Over Source: The Key to Effective Data Mixing for Language Models Pre-training","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2508.20869","title":"OLMoASR: Open Models and Data for Training Robust Speech Recognition Models","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2510.16713","title":"so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs","created":"2025-10-19","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","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":"2601.18302","title":"Suppressing Final Layer Hidden State Jumps in Transformer Pretraining","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2603.10033","title":"Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights","created":"2026-02-28","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":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2504.06219","title":"Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.20331","title":"Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2512.07612","title":"PCMind-2.1-Kaiyuan-2B Technical Report","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2601.16018","title":"Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2606.11499","title":"Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.19468","title":"Characterizing Narrative Content in Web-scale LLM Pretraining Data","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2505.16570","title":"URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.02297","title":"Interactive Training: Feedback-Driven Neural Network Optimization","created":"2025-10-02","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":"2606.08167","title":"Explaining Data Mixing Scaling Laws","created":"2026-06-06","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":"2511.01090","title":"Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2511.21613","title":"Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.07522","title":"LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.13972","title":"FLUX: Data Worth Training On","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.06892","title":"GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.15216","title":"Spokes: Optimizing for Diverse Pretraining Data Selection","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.19625","title":"Capability Provenance in Language Models: A Case Study in Social Reasoning","created":"2026-06-17","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":"2606.24644","title":"Measuring User's Mental Models of Speech Translation in Human-AI Collaboration","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.26277","title":"From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02266","title":"HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.27928","title":"Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.40295","title":"How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.20456","title":"The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}