{"list":"other","total":66,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"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":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"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":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"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":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1602.02410","title":"Exploring the Limits of Language Modeling","created":"2016-02-07","cited_by_count":173},{"id":"1909.03242","title":"MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims","created":"2019-09-07","cited_by_count":169},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2007.04068","title":"Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence","created":"2020-07-08","cited_by_count":101},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"2109.09115","title":"Do Long-Range Language Models Actually Use Long-Range Context?","created":"2021-09-19","cited_by_count":92},{"id":"1911.09723","title":"Fast Sparse ConvNets","created":"2019-11-21","cited_by_count":86},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56},{"id":"1606.09274","title":"Compression of Neural Machine Translation Models via Pruning","created":"2016-06-29","cited_by_count":44},{"id":"2103.04044","title":"Putting Humans in the Natural Language Processing Loop: A Survey","created":"2021-03-06","cited_by_count":40},{"id":"2004.14340","title":"WoodFisher: Efficient Second-Order Approximation for Neural Network Compression","created":"2020-04-29","cited_by_count":21},{"id":"2106.00950","title":"A Multi-Level Attention Model for Evidence-Based Fact Checking","created":"2021-06-02","cited_by_count":13},{"id":"2103.00752","title":"Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence","created":"2021-03-01","cited_by_count":10},{"id":"2011.03292","title":"Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning","created":"2020-11-06","cited_by_count":7}],"next_cursor":null}