{"list":"other","total":61,"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"1901.05287","title":"Assessing BERT's Syntactic Abilities","created":"2019-01-16","cited_by_count":192},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"2002.09599","title":"Training Question Answering Models From Synthetic Data","created":"2020-02-22","cited_by_count":95},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2109.09193","title":"Towards Zero-Label Language Learning","created":"2021-09-19","cited_by_count":76},{"id":"2009.07602","title":"UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation","created":"2020-09-16","cited_by_count":60},{"id":"1611.08562","title":"A Simple, Fast Diverse Decoding Algorithm for Neural Generation","created":"2016-11-25","cited_by_count":58},{"id":"2102.01335","title":"Neural Data Augmentation via Example Extrapolation","created":"2021-02-02","cited_by_count":54},{"id":"2201.06910","title":"ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization","created":"2022-01-18","cited_by_count":54},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52},{"id":"1406.2080","title":"Training Convolutional Networks with Noisy Labels","created":"2014-06-09","cited_by_count":48},{"id":"2105.11134","title":"One2Set: Generating Diverse Keyphrases as a Set","created":"2021-05-24","cited_by_count":41},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33},{"id":"2112.15278","title":"Data-Free Knowledge Transfer: A Survey","created":"2021-12-31","cited_by_count":31},{"id":"1911.03587","title":"How Decoding Strategies Affect the Verifiability of Generated Text","created":"2019-11-09","cited_by_count":27},{"id":"2012.15495","title":"Towards Zero-Shot Knowledge Distillation for Natural Language Processing","created":"2020-12-31","cited_by_count":20},{"id":"1901.10008","title":"The OoO VLIW JIT Compiler for GPU Inference","created":"2019-01-28","cited_by_count":4}],"next_cursor":null}