{"list":"other","total":59,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"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":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1909.01326","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","created":"2019-09-03","cited_by_count":541},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"1402.0030","title":"Neural Variational Inference and Learning in Belief Networks","created":"2014-01-31","cited_by_count":117},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"2004.11714","title":"Residual Energy-Based Models for Text Generation","created":"2020-04-22","cited_by_count":95},{"id":"1301.2315","title":"The Optimal Reward Baseline for Gradient-Based Reinforcement Learning","created":"2013-01-10","cited_by_count":85},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"1705.09156","title":"The free energy principle for action and perception: A mathematical review","created":"2017-05-24","cited_by_count":66},{"id":"1511.06350","title":"Structured Prediction Energy Networks","created":"2015-11-19","cited_by_count":59},{"id":"2012.08561","title":"Pre-Training Transformers as Energy-Based Cloze Models","created":"2020-12-15","cited_by_count":52},{"id":"1809.10736","title":"Controllable Neural Story Plot Generation via Reward Shaping","created":"2018-09-27","cited_by_count":49},{"id":"2009.13267","title":"Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models","created":"2020-09-20","cited_by_count":44},{"id":"2005.00850","title":"ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation","created":"2020-05-02","cited_by_count":34},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32},{"id":"1603.06042","title":"Globally Normalized Transition-Based Neural Networks","created":"2016-03-19","cited_by_count":26},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21},{"id":"1912.08517","title":"Distributional Reinforcement Learning for Energy-Based Sequential Models","created":"2019-12-18","cited_by_count":17},{"id":"1909.07063","title":"Global Autoregressive Models for Data-Efficient Sequence Learning","created":"2019-09-16","cited_by_count":15},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15},{"id":"2101.06829","title":"Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models","created":"2021-01-18","cited_by_count":14},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10},{"id":"2106.04985","title":"Energy-Based Models for Code Generation under Compilability Constraints","created":"2021-06-09","cited_by_count":10},{"id":"2004.10188","title":"Residual Energy-Based Models for Text","created":"2020-04-06","cited_by_count":5}],"next_cursor":null}