{"list":"other","total":55,"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":"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":"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1906.05474","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","created":"2019-06-13","cited_by_count":299},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142},{"id":"1904.01608","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","created":"2019-04-02","cited_by_count":130},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116},{"id":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101},{"id":"2106.03598","title":"SciFive: a text-to-text transformer model for biomedical literature","created":"2021-05-28","cited_by_count":99},{"id":"2010.14235","title":"Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles","created":"2020-10-27","cited_by_count":97},{"id":"1902.09476","title":"MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts","created":"2019-02-25","cited_by_count":80},{"id":"1806.04185","title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","created":"2018-06-11","cited_by_count":79},{"id":"2003.11515","title":"Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings","created":"2020-03-11","cited_by_count":79},{"id":"2109.13532","title":"Template-free Prompt Tuning for Few-shot NER","created":"2021-09-28","cited_by_count":73},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57},{"id":"2201.06910","title":"ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization","created":"2022-01-18","cited_by_count":54},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51},{"id":"2005.14672","title":"Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP","created":"2020-05-29","cited_by_count":50},{"id":"2008.13546","title":"Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs","created":"2020-08-04","cited_by_count":48},{"id":"2005.04177","title":"Evidence Inference 2.0: More Data, Better Models","created":"2020-05-08","cited_by_count":40},{"id":"2005.06376","title":"BIOMRC: A Dataset for Biomedical Machine Reading Comprehension","created":"2020-05-13","cited_by_count":35},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33},{"id":"2104.03879","title":"COVID-19 Named Entity Recognition for Vietnamese","created":"2021-04-08","cited_by_count":19},{"id":"2008.01972","title":"Ontology-driven weak supervision for clinical entity classification in electronic health records","created":"2020-08-05","cited_by_count":18},{"id":"2011.02832","title":"Pitfalls in Machine Learning Research: Reexamining the Development Cycle","created":"2020-11-04","cited_by_count":17},{"id":"1905.01852","title":"A Large Parallel Corpus of Full-Text Scientific Articles","created":"2019-05-06","cited_by_count":12},{"id":"2003.12218","title":"Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision","created":"2020-03-27","cited_by_count":12},{"id":"2204.03637","title":"tmVar 3.0: an improved variant concept recognition and normalization tool","created":"2022-04-07","cited_by_count":10},{"id":"2010.16218","title":"Biomedical Concept Relatedness -- A large EHR-based benchmark","created":"2020-10-30","cited_by_count":4}],"next_cursor":null}