{"total":19,"rows":[{"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":"2503.12347","title":"Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs","created":"2025-03-16","cited_by_count":16,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2506.07109","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","created":"2025-06-08","cited_by_count":7,"area":null},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2504.17562","title":"When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2603.27435","title":"Improving Attributed Long-form Question Answering with Intent Awareness","created":"2026-03-28","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":"2502.00761","title":"FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2502.14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2503.13383","title":"Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning","created":"2025-03-17","cited_by_count":1,"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":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.12397","title":"KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2507.19419","title":"TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2601.15236","title":"MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2610.00234","title":"Conflicting Supervision Moves Commitment, Not Capability: A 12.29{\\sigma} arrangement effect that is exactly zero under a convention-agnostic score","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}