{"list":"other","total":64,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"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":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"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":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"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":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"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":"1511.01844","title":"A note on the evaluation of generative models","created":"2015-11-05","cited_by_count":292},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"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":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"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":"1612.02136","title":"Mode Regularized Generative Adversarial Networks","created":"2016-12-07","cited_by_count":123},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"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":"1811.10996","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","created":"2018-11-14","cited_by_count":94},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1511.05101","title":"How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?","created":"2015-11-16","cited_by_count":78},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"1809.10736","title":"Controllable Neural Story Plot Generation via Reward Shaping","created":"2018-09-27","cited_by_count":49},{"id":"2106.01465","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","created":"2021-06-02","cited_by_count":46},{"id":"2108.07790","title":"Mitigating harm in language models with conditional-likelihood filtration","created":"2021-08-04","cited_by_count":40},{"id":"2106.02736","title":"Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings","created":"2021-06-04","cited_by_count":37},{"id":"2206.11684","title":"Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models","created":"2022-06-23","cited_by_count":35},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32},{"id":"1810.11943","title":"Variational Inference with Tail-adaptive f-Divergence","created":"2018-10-29","cited_by_count":25},{"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}],"next_cursor":null}