{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2106.01144","title":"Towards Emotional Support Dialog Systems","created":"2021-06-02","cited_by_count":299},{"id":"2010.07079","title":"Recipes for Safety in Open-domain Chatbots","created":"2020-10-14","cited_by_count":170},{"id":"1910.07931","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","created":"2019-10-17","cited_by_count":145},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134},{"id":"1911.03860","title":"Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training","created":"2019-11-10","cited_by_count":110},{"id":"2005.03954","title":"Towards Conversational Recommendation over Multi-Type Dialogs","created":"2020-05-08","cited_by_count":107},{"id":"2106.01702","title":"PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support","created":"2021-06-03","cited_by_count":92},{"id":"2109.05739","title":"CEM: Commonsense-aware Empathetic Response Generation","created":"2021-09-13","cited_by_count":89},{"id":"1906.05572","title":"Proactive Human-Machine Conversation with Explicit Conversation Goals","created":"2019-06-13","cited_by_count":88},{"id":"1909.03087","title":"ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons","created":"2019-09-06","cited_by_count":83},{"id":"2109.05729","title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation","created":"2021-09-13","cited_by_count":81},{"id":"2006.16779","title":"PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning","created":"2020-06-30","cited_by_count":79},{"id":"2008.03946","title":"A Large-Scale Chinese Short-Text Conversation Dataset","created":"2020-08-10","cited_by_count":77},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73},{"id":"2012.13391","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","created":"2020-12-24","cited_by_count":68},{"id":"2012.00413","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","created":"2020-12-01","cited_by_count":60},{"id":"2004.04100","title":"KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation","created":"2020-04-08","cited_by_count":59},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52},{"id":"1911.09969","title":"The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service","created":"2019-11-22","cited_by_count":47},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46},{"id":"2110.06696","title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","created":"2021-10-13","cited_by_count":45},{"id":"2105.08316","title":"CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation","created":"2021-05-18","cited_by_count":42},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39},{"id":"2109.09519","title":"PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation","created":"2021-09-20","cited_by_count":37},{"id":"2103.02548","title":"NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation","created":"2021-03-03","cited_by_count":35},{"id":"2110.04725","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","created":"2021-10-10","cited_by_count":35},{"id":"2108.01547","title":"EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training","created":"2021-08-03","cited_by_count":34},{"id":"2112.07924","title":"Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation","created":"2021-12-15","cited_by_count":32},{"id":"2108.12960","title":"LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation","created":"2021-08-30","cited_by_count":24}],"next_cursor":null}