{"list":"other","total":77,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94},{"id":"2310.15393","title":"DoGE: Domain Reweighting with Generalization Estimation","created":"2023-10-23","cited_by_count":90},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43},{"id":"2505.18949","title":"The Price of Format: Diversity Collapse in LLMs","created":"2025-05-25","cited_by_count":43},{"id":"2508.15096","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset","created":"2025-08-20","cited_by_count":38},{"id":"2408.09869","title":"Docling Technical Report","created":"2024-08-19","cited_by_count":34},{"id":"2502.12150","title":"Idiosyncrasies in Large Language Models","created":"2025-02-17","cited_by_count":33},{"id":"2506.05209","title":"The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text","created":"2025-06-05","cited_by_count":31},{"id":"2401.06408","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","created":"2024-01-12","cited_by_count":22},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20},{"id":"2204.10878","title":"ChapterBreak: A Challenge Dataset for Long-Range Language Models","created":"2022-04-22","cited_by_count":18},{"id":"1905.04271","title":"Mutual Information Scaling and Expressive Power of Sequence Models","created":"2019-05-10","cited_by_count":14},{"id":"2503.02502","title":"LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs","created":"2025-03-04","cited_by_count":11},{"id":"2305.06615","title":"Autocorrelations Decay in Texts and Applicability Limits of Language Models","created":"2023-05-11","cited_by_count":9},{"id":"2412.04318","title":"The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation","created":"2024-12-05","cited_by_count":9},{"id":"2502.16860","title":"LongAttn: Selecting Long-context Training Data via Token-level Attention","created":"2025-02-24","cited_by_count":9},{"id":"2511.23119","title":"Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM","created":"2025-11-28","cited_by_count":8},{"id":"2506.08300","title":"Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability","created":"2025-06-10","cited_by_count":7},{"id":"2511.16893","title":"Predicting the Emergence of Induction Heads in Language Model Pretraining","created":"2025-11-21","cited_by_count":7},{"id":"2401.17658","title":"Document Structure in Long Document Transformers","created":"2024-01-31","cited_by_count":6},{"id":"2504.01542","title":"Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation","created":"2025-04-02","cited_by_count":6},{"id":"2506.01789","title":"Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability","created":"2025-06-02","cited_by_count":6},{"id":"2602.12414","title":"propella-1: Multi-Property Document Annotation for LLM Data Curation at Scale","created":"2026-02-12","cited_by_count":6},{"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},{"id":"2412.02857","title":"Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training","created":"2024-12-03","cited_by_count":5},{"id":"2510.02330","title":"EntropyLong: Effective Long-Context Training via Predictive Uncertainty","created":"2025-09-26","cited_by_count":5},{"id":"2011.04163","title":"Chapter Captor: Text Segmentation in Novels","created":"2020-11-09","cited_by_count":4},{"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},{"id":"2510.25804","title":"Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data","created":"2025-10-29","cited_by_count":4},{"id":"2511.16397","title":"AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser","created":"2025-11-20","cited_by_count":4},{"id":"2602.19548","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining","created":"2026-02-23","cited_by_count":4},{"id":"2605.10544","title":"Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing","created":"2026-05-11","cited_by_count":4},{"id":"2606.16246","title":"Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining","created":"2026-06-15","cited_by_count":4},{"id":"2604.03616","title":"The Format Tax","created":"2026-04-04","cited_by_count":3},{"id":"2607.09657","title":"Scalable Visual Pretraining for Language Intelligence","created":"2026-07-10","cited_by_count":3},{"id":"2607.28109","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","created":"2026-07-30","cited_by_count":3},{"id":"2503.03705","title":"Enhancing LLM Knowledge Learning through Generalization","created":"2025-03-05","cited_by_count":2},{"id":"2603.27006","title":"The Last Fingerprint: How Markdown Training Shapes LLM Prose","created":"2026-03-27","cited_by_count":2},{"id":"2606.11499","title":"Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality","created":"2026-06-09","cited_by_count":2},{"id":"2606.11643","title":"Improving Cross-Format Robustness in Language Models with Multi-Format Training","created":"2026-06-10","cited_by_count":2},{"id":"2606.19468","title":"Characterizing Narrative Content in Web-scale LLM Pretraining Data","created":"2026-06-17","cited_by_count":2},{"id":"2606.28344","title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","created":"2026-06-01","cited_by_count":2},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2},{"id":"1912.07506","title":"Scale-dependent Relationships in Natural Language","created":"2019-12-16","cited_by_count":1},{"id":"2602.15968","title":"From Reflection to Repair: A Scoping Review of Dataset Documentation Tools","created":"2026-02-17","cited_by_count":1},{"id":"2604.13006","title":"One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness","created":"2026-04-14","cited_by_count":1},{"id":"2604.16380","title":"Data Mixing for Large Language Models Pretraining: A Survey and Outlook","created":"2026-03-25","cited_by_count":1},{"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},{"id":"2605.27878","title":"Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction","created":"2026-05-27","cited_by_count":1},{"id":"2606.11198","title":"The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content","created":"2026-04-21","cited_by_count":1},{"id":"2606.24077","title":"Sentence-Level Contextual Entrainment in Large Language Models","created":"2026-06-23","cited_by_count":1},{"id":"2608.04330","title":"Right Reset: Chunking by Prefix Removal","created":"2026-08-05","cited_by_count":1}],"next_cursor":null}