{"list":"other","total":67,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"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":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1806.05759","title":"Insights on representational similarity in neural networks with canonical correlation","created":"2018-06-14","cited_by_count":324},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175},{"id":"2004.12651","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","created":"2020-04-27","cited_by_count":170},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124},{"id":"2002.10365","title":"The Early Phase of Neural Network Training","created":"2020-02-24","cited_by_count":115},{"id":"2004.14448","title":"What Happens To BERT Embeddings During Fine-tuning?","created":"2020-04-29","cited_by_count":113},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"2104.07885","title":"Probing Across Time: What Does RoBERTa Know and When?","created":"2021-04-16","cited_by_count":73},{"id":"1904.05506","title":"Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?","created":"2019-04-11","cited_by_count":71},{"id":"2010.10907","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","created":"2020-10-21","cited_by_count":71},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64},{"id":"2003.10933","title":"Learn to Forget: Machine Unlearning via Neuron Masking","created":"2020-03-24","cited_by_count":62},{"id":"2110.02406","title":"Word Acquisition in Neural Language Models","created":"2021-10-05","cited_by_count":41},{"id":"2006.07490","title":"Understanding Unintended Memorization in Federated Learning","created":"2020-06-12","cited_by_count":36},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36},{"id":"2010.02480","title":"Pretrained Language Model Embryology: The Birth of ALBERT","created":"2020-10-06","cited_by_count":30},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29},{"id":"2110.08370","title":"Training Dynamics for Text Summarization Models","created":"2021-10-15","cited_by_count":25},{"id":"2203.03910","title":"Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation","created":"2022-03-08","cited_by_count":18},{"id":"1811.01640","title":"Leveraging Random Label Memorization for Unsupervised Pre-Training","created":"2018-11-05","cited_by_count":12},{"id":"1606.08370","title":"The right time to learn: mechanisms and optimization of spaced learning","created":"2016-06-27","cited_by_count":5},{"id":"2109.01844","title":"On robustness of generative representations against catastrophic forgetting","created":"2021-09-04","cited_by_count":5}],"next_cursor":null}