{"list":"other","total":51,"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":"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"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":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"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":"1907.05774","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","created":"2019-07-12","cited_by_count":110},{"id":"2009.12005","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","created":"2020-09-25","cited_by_count":103},{"id":"2006.16779","title":"PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning","created":"2020-06-30","cited_by_count":79},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64},{"id":"1908.01946","title":"Dialog State Tracking: A Neural Reading Comprehension Approach","created":"2019-08-06","cited_by_count":62},{"id":"2304.06556","title":"Are LLMs All You Need for Task-Oriented Dialogue?","created":"2023-04-13","cited_by_count":54},{"id":"2109.04655","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","created":"2021-09-10","cited_by_count":52},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34},{"id":"2109.04645","title":"CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-09-10","cited_by_count":30},{"id":"2205.10400","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","created":"2022-05-20","cited_by_count":30},{"id":"2011.03023","title":"Language Model is All You Need: Natural Language Understanding as Question Answering","created":"2020-11-05","cited_by_count":29},{"id":"2103.10518","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","created":"2021-03-18","cited_by_count":23},{"id":"2010.11791","title":"ConVEx: Data-Efficient and Few-Shot Slot Labeling","created":"2020-10-22","cited_by_count":22},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21},{"id":"2108.12589","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-08-28","cited_by_count":18},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15},{"id":"2004.01972","title":"Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks","created":"2020-04-04","cited_by_count":14},{"id":"2204.02123","title":"Improved and Efficient Conversational Slot Labeling through Question Answering","created":"2022-04-05","cited_by_count":10}],"next_cursor":null}