{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1806.01246","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","created":"2018-06-04","cited_by_count":498},{"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":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"1908.11229","title":"White-box vs Black-box: Bayes Optimal Strategies for Membership Inference","created":"2019-08-29","cited_by_count":271},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"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":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2002.02561","title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","created":"2020-02-07","cited_by_count":200},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88},{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85},{"id":"2011.03321","title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition","created":"2020-11-04","cited_by_count":76},{"id":"2407.07263","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models","created":"2024-07-09","cited_by_count":72},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56},{"id":"2310.17589","title":"An Open Source Data Contamination Report for Large Language Models","created":"2023-10-26","cited_by_count":51},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50},{"id":"2407.14981","title":"Open Problems in Technical AI Governance","created":"2024-07-20","cited_by_count":49},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40},{"id":"2406.04391","title":"Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?","created":"2024-06-06","cited_by_count":40},{"id":"2303.14151","title":"Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle","created":"2023-03-24","cited_by_count":37},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33},{"id":"2407.07565","title":"On Leakage of Code Generation Evaluation Datasets","created":"2024-07-10","cited_by_count":32},{"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":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30},{"id":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29},{"id":"2310.03262","title":"Predicting Emergent Abilities with Infinite Resolution Evaluation","created":"2023-10-05","cited_by_count":28},{"id":"2406.13236","title":"Data Contamination Can Cross Language Barriers","created":"2024-06-19","cited_by_count":26},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25},{"id":"2409.01790","title":"Training on the Benchmark Is Not All You Need","created":"2024-09-03","cited_by_count":25},{"id":"2505.18773","title":"Exploring the limits of strong membership inference attacks on large language models","created":"2025-05-24","cited_by_count":22},{"id":"2503.17514","title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On","created":"2025-03-21","cited_by_count":21},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20},{"id":"2508.13180","title":"Search-Time Data Contamination","created":"2025-08-12","cited_by_count":19},{"id":"2510.19811","title":"Hubble: a Model Suite to Advance the Study of LLM Memorization","created":"2025-10-22","cited_by_count":17},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14},{"id":"2501.18771","title":"Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation","created":"2025-01-30","cited_by_count":13},{"id":"2506.13681","title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","created":"2025-06-16","cited_by_count":10},{"id":"2508.17580","title":"UQ: Assessing Language Models on Unsolved Questions","created":"2025-08-25","cited_by_count":9},{"id":"2503.07879","title":"Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality","created":"2025-03-10","cited_by_count":8},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5},{"id":"2601.06103","title":"The Impact of Post-training on Data Contamination","created":"2026-01-03","cited_by_count":5},{"id":"2303.03648","title":"Can Membership Inferencing be Refuted?","created":"2023-03-07","cited_by_count":4},{"id":"2508.02037","title":"Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time","created":"2025-08-04","cited_by_count":4},{"id":"2506.06003","title":"What Really is a Member? Discrediting Membership Inference via Poisoning","created":"2025-06-06","cited_by_count":2}],"next_cursor":null}