{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"1708.02709","title":"Recent Trends in Deep Learning Based Natural Language Processing","created":"2017-08-09","cited_by_count":263},{"id":"1911.00650","title":"Automatic Detection of Generated Text is Easiest when Humans are Fooled","created":"2019-11-02","cited_by_count":261},{"id":"2010.11784","title":"Self-Alignment Pretraining for Biomedical Entity Representations","created":"2020-10-22","cited_by_count":237},{"id":"2203.12277","title":"Unified Structure Generation for Universal Information Extraction","created":"2022-03-23","cited_by_count":221},{"id":"2205.12689","title":"Large Language Models are Few-Shot Clinical Information Extractors","created":"2022-05-25","cited_by_count":207},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2004.13625","title":"Event Extraction by Answering (Almost) Natural Questions","created":"2020-04-28","cited_by_count":177},{"id":"2008.12009","title":"A Survey of Evaluation Metrics Used for NLG Systems","created":"2020-08-27","cited_by_count":164},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104},{"id":"1912.02047","title":"Neural Machine Translation: A Review and Survey","created":"2019-12-04","cited_by_count":100},{"id":"2012.04281","title":"CTRLsum: Towards Generic Controllable Text Summarization","created":"2020-12-08","cited_by_count":98},{"id":"2302.08091","title":"Do We Still Need Clinical Language Models?","created":"2023-02-16","cited_by_count":98},{"id":"2203.08410","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","created":"2022-03-16","cited_by_count":83},{"id":"1905.08284","title":"Enriching Pre-trained Language Model with Entity Information for Relation Classification","created":"2019-05-20","cited_by_count":82},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82},{"id":"2008.00364","title":"A Survey on Text Classification: From Shallow to Deep Learning","created":"2020-08-02","cited_by_count":80},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"2109.07589","title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","created":"2021-09-15","cited_by_count":64},{"id":"2105.08645","title":"CoTexT: Multi-task Learning with Code-Text Transformer","created":"2021-05-18","cited_by_count":61},{"id":"2202.12109","title":"Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction","created":"2022-02-24","cited_by_count":54},{"id":"1810.05241","title":"One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases","created":"2018-10-11","cited_by_count":52},{"id":"2109.06067","title":"Packed Levitated Marker for Entity and Relation Extraction","created":"2021-09-13","cited_by_count":49},{"id":"2304.01938","title":"Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physics","created":"2023-04-01","cited_by_count":49},{"id":"2303.09038","title":"Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential","created":"2023-03-16","cited_by_count":39},{"id":"2210.03568","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","created":"2022-10-07","cited_by_count":38},{"id":"2209.02235","title":"Automatic Code Documentation Generation Using GPT-3","created":"2022-09-06","cited_by_count":37},{"id":"2112.08547","title":"Learning Rich Representation of Keyphrases from Text","created":"2021-12-16","cited_by_count":36},{"id":"1512.05742","title":"A Survey of Available Corpora for Building Data-Driven Dialogue Systems","created":"2015-12-17","cited_by_count":33},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32},{"id":"2106.00874","title":"Conversational Question Answering: A Survey","created":"2021-06-02","cited_by_count":31},{"id":"2205.07557","title":"Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data","created":"2022-05-16","cited_by_count":27},{"id":"2009.10229","title":"An Empirical Study on Neural Keyphrase Generation","created":"2020-09-22","cited_by_count":25},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23},{"id":"2212.09656","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","created":"2022-12-19","cited_by_count":23},{"id":"2012.15515","title":"Neural Machine Translation: A Review of Methods, Resources, and Tools","created":"2020-12-31","cited_by_count":19},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16},{"id":"2210.14502","title":"SentBS: Sentence-level Beam Search for Controllable Summarization","created":"2022-10-26","cited_by_count":10},{"id":"2305.02220","title":"WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models","created":"2023-05-03","cited_by_count":7},{"id":"2006.04014","title":"Medical Concept Normalization in User Generated Texts by Learning Target Concept Embeddings","created":"2020-06-07","cited_by_count":2},{"id":"2301.06606","title":"PromptShots at the FinNLP-2022 ERAI Tasks: Pairwise Comparison and Unsupervised Ranking","created":"2023-01-16","cited_by_count":2}],"next_cursor":null}