{"list":"other","total":81,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"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":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"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":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134},{"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":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"1906.04701","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","created":"2019-06-11","cited_by_count":101},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62},{"id":"2106.03634","title":"PROST: Physical Reasoning of Objects through Space and Time","created":"2021-06-07","cited_by_count":48},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43},{"id":"1705.08807","title":"When Will AI Exceed Human Performance? Evidence from AI Experts","created":"2017-05-24","cited_by_count":41},{"id":"1906.06669","title":"One Epoch Is All You Need","created":"2019-06-16","cited_by_count":41},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35},{"id":"1902.09469","title":"Embedded Agency","created":"2019-02-25","cited_by_count":19},{"id":"2011.02832","title":"Pitfalls in Machine Learning Research: Reexamining the Development Cycle","created":"2020-11-04","cited_by_count":17},{"id":"1710.05060","title":"Functional Decision Theory: A New Theory of Instrumental Rationality","created":"2017-10-13","cited_by_count":7},{"id":"2103.15345","title":"FixNorm: Dissecting Weight Decay for Training Deep Neural Networks","created":"2021-03-29","cited_by_count":3},{"id":"2111.04439","title":"Addressing Privacy Threats from Machine Learning","created":"2021-10-25","cited_by_count":1}],"next_cursor":null}