{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"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":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"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":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"1903.07571","title":"Two models of double descent for weak features","created":"2019-03-18","cited_by_count":195},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"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":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159},{"id":"2009.14286","title":"Benign overfitting in ridge regression","created":"2020-09-29","cited_by_count":153},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113},{"id":"2402.01092","title":"A Dynamical Model of Neural Scaling Laws","created":"2024-02-02","cited_by_count":111},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77},{"id":"2404.10102","title":"Chinchilla Scaling: A replication attempt","created":"2024-04-15","cited_by_count":72},{"id":"1906.06669","title":"One Epoch Is All You Need","created":"2019-06-16","cited_by_count":41},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4}],"next_cursor":null}