{"list":"other","total":52,"rows":[{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"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":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"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":"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":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"1908.06083","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","created":"2019-08-17","cited_by_count":176},{"id":"2010.07079","title":"Recipes for Safety in Open-domain Chatbots","created":"2020-10-14","cited_by_count":170},{"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":"1611.00179","title":"Dual Learning for Machine Translation","created":"2016-11-01","cited_by_count":148},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"1812.07626","title":"Universal Successor Features Approximators","created":"2018-12-18","cited_by_count":103},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1606.02396","title":"Deep Successor Reinforcement Learning","created":"2016-06-08","cited_by_count":72},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64},{"id":"2005.01822","title":"Exploring Controllable Text Generation Techniques","created":"2020-05-04","cited_by_count":55},{"id":"1704.03084","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","created":"2017-04-10","cited_by_count":44},{"id":"1705.07830","title":"Ask the Right Questions: Active Question Reformulation with Reinforcement Learning","created":"2017-05-22","cited_by_count":44},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38},{"id":"1609.00777","title":"Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access","created":"2016-09-03","cited_by_count":36},{"id":"2210.09551","title":"DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation","created":"2022-10-18","cited_by_count":30},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28},{"id":"1707.00130","title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","created":"2017-07-01","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":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16},{"id":"1606.03152","title":"Policy Networks with Two-Stage Training for Dialogue Systems","created":"2016-06-10","cited_by_count":14},{"id":"1711.00106","title":"DCN+: Mixed Objective and Deep Residual Coattention for Question Answering","created":"2017-10-31","cited_by_count":12},{"id":"1704.00756","title":"Multi-Advisor Reinforcement Learning","created":"2017-04-03","cited_by_count":7},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","cited_by_count":4}],"next_cursor":null}