{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2005.02877","title":"TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking","created":"2020-05-06","cited_by_count":130},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124},{"id":"2012.03539","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","created":"2020-12-07","cited_by_count":111},{"id":"2009.12005","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","created":"2020-09-25","cited_by_count":103},{"id":"2111.14592","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","created":"2021-11-29","cited_by_count":102},{"id":"1911.10484","title":"Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context","created":"2019-11-24","cited_by_count":99},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88},{"id":"1911.03906","title":"Efficient Dialogue State Tracking by Selectively Overwriting Memory","created":"2019-11-10","cited_by_count":76},{"id":"1908.01946","title":"Dialog State Tracking: A Neural Reading Comprehension Approach","created":"2019-08-06","cited_by_count":62},{"id":"2401.06468","title":"Adapting Large Language Models for Document-Level Machine Translation","created":"2024-01-12","cited_by_count":59},{"id":"2304.06556","title":"Are LLMs All You Need for Task-Oriented Dialogue?","created":"2023-04-13","cited_by_count":54},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49},{"id":"2009.08115","title":"A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning","created":"2020-09-17","cited_by_count":47},{"id":"1704.03084","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","created":"2017-04-10","cited_by_count":44},{"id":"1911.06192","title":"Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering","created":"2019-11-07","cited_by_count":39},{"id":"1908.10719","title":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","created":"2019-08-28","cited_by_count":37},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30},{"id":"2004.03809","title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition","created":"2020-04-08","cited_by_count":23},{"id":"1909.00754","title":"Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation","created":"2019-09-02","cited_by_count":21},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19},{"id":"2103.06648","title":"Domain State Tracking for a Simplified Dialogue System","created":"2021-03-11","cited_by_count":17},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16},{"id":"1906.00499","title":"Budgeted Policy Learning for Task-Oriented Dialogue Systems","created":"2019-06-02","cited_by_count":13},{"id":"1811.07550","title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning","created":"2018-11-19","cited_by_count":12},{"id":"1803.03232","title":"Feudal Reinforcement Learning for Dialogue Management in Large Domains","created":"2018-03-08","cited_by_count":11},{"id":"2009.09781","title":"Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems","created":"2020-09-21","cited_by_count":10},{"id":"1804.07855","title":"Subgoal Discovery for Hierarchical Dialogue Policy Learning","created":"2018-04-20","cited_by_count":9},{"id":"2211.16773","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning","created":"2022-11-30","cited_by_count":9},{"id":"1808.06497","title":"Goal-oriented Dialogue Policy Learning from Failures","created":"2018-08-20","cited_by_count":8},{"id":"1911.08151","title":"Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation","created":"2019-11-19","cited_by_count":6},{"id":"2005.11729","title":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","created":"2020-05-24","cited_by_count":6}],"next_cursor":null}