{"list":"other","total":76,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"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":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"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":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"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":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"1904.03035","title":"Identifying and Reducing Gender Bias in Word-Level Language Models","created":"2019-04-05","cited_by_count":214},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"1606.02960","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","created":"2016-06-09","cited_by_count":127},{"id":"1906.02448","title":"Bridging the Gap between Training and Inference for Neural Machine Translation","created":"2019-06-06","cited_by_count":123},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"1512.02433","title":"Minimum Risk Training for Neural Machine Translation","created":"2015-12-08","cited_by_count":115},{"id":"2005.00268","title":"Towards Controllable Biases in Language Generation","created":"2020-05-01","cited_by_count":112},{"id":"1911.03860","title":"Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training","created":"2019-11-10","cited_by_count":110},{"id":"1702.08138","title":"Deceiving Google's Perspective API Built for Detecting Toxic Comments","created":"2017-02-27","cited_by_count":102},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1908.09368","title":"Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer","created":"2019-08-25","cited_by_count":81},{"id":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"1804.06451","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","created":"2018-04-17","cited_by_count":73},{"id":"2005.07064","title":"Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning","created":"2020-05-14","cited_by_count":66},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57},{"id":"1711.04956","title":"Classical Structured Prediction Losses for Sequence to Sequence Learning","created":"2017-11-14","cited_by_count":55},{"id":"1809.10736","title":"Controllable Neural Story Plot Generation via Reward Shaping","created":"2018-09-27","cited_by_count":49},{"id":"2005.00820","title":"Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing","created":"2020-05-02","cited_by_count":41},{"id":"2010.00685","title":"How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds","created":"2020-10-01","cited_by_count":35},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32},{"id":"1810.04777","title":"Rao-Blackwellized Stochastic Gradients for Discrete Distributions","created":"2018-10-10","cited_by_count":24},{"id":"1704.06933","title":"Adversarial Neural Machine Translation","created":"2017-04-20","cited_by_count":21},{"id":"1908.10909","title":"Interactive Language Learning by Question Answering","created":"2019-08-28","cited_by_count":19},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18},{"id":"1603.07954","title":"Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning","created":"2016-03-25","cited_by_count":16},{"id":"2112.08593","title":"Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning","created":"2021-12-16","cited_by_count":14},{"id":"1908.10449","title":"Interactive Machine Comprehension with Information Seeking Agents","created":"2019-08-27","cited_by_count":13},{"id":"1711.00106","title":"DCN+: Mixed Objective and Deep Residual Coattention for Question Answering","created":"2017-10-31","cited_by_count":12},{"id":"1907.02848","title":"Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes","created":"2019-07-05","cited_by_count":11},{"id":"1808.09658","title":"APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning","created":"2018-08-29","cited_by_count":9},{"id":"2201.12320","title":"Generative Cooperative Networks for Natural Language Generation","created":"2022-01-28","cited_by_count":8},{"id":"1806.03290","title":"Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing","created":"2018-06-08","cited_by_count":5},{"id":"2007.07196","title":"Investigation of Sentiment Controllable Chatbot","created":"2020-07-11","cited_by_count":2}],"next_cursor":null}