{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"1912.00741","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter","created":"2019-12-02","cited_by_count":210},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"1412.6856","title":"Object Detectors Emerge in Deep Scene CNNs","created":"2014-12-22","cited_by_count":179},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1512.08571","title":"Structured Pruning of Deep Convolutional Neural Networks","created":"2015-12-29","cited_by_count":149},{"id":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","cited_by_count":148},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"1803.06959","title":"On the importance of single directions for generalization","created":"2018-03-19","cited_by_count":99},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62},{"id":"1911.03864","title":"Improving Transformer Models by Reordering their Sublayers","created":"2019-11-10","cited_by_count":52},{"id":"2010.02812","title":"Intrinsic Probing through Dimension Selection","created":"2020-10-06","cited_by_count":45},{"id":"1407.1610","title":"Analyzing the Performance of Multilayer Neural Networks for Object Recognition","created":"2014-07-07","cited_by_count":29},{"id":"2005.07647","title":"Finding Experts in Transformer Models","created":"2020-05-15","cited_by_count":28}],"next_cursor":null}