{"list":"other","total":52,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"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":"1903.12394","title":"Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems","created":"2019-03-29","cited_by_count":205},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203},{"id":"2303.16854","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","created":"2023-03-29","cited_by_count":172},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"id":"2112.01640","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","created":"2021-12-02","cited_by_count":143},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139},{"id":"2109.04270","title":"Toward a Perspectivist Turn in Ground Truthing for Predictive Computing","created":"2021-09-09","cited_by_count":130},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2310.03668","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","created":"2023-10-05","cited_by_count":119},{"id":"2010.02559","title":"LEGAL-BERT: The Muppets straight out of Law School","created":"2020-10-06","cited_by_count":111},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96},{"id":"2006.03644","title":"Stance Detection on Social Media: State of the Art and Trends","created":"2020-06-05","cited_by_count":95},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94},{"id":"2310.15638","title":"CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation","created":"2023-10-24","cited_by_count":94},{"id":"2305.06626","title":"When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks","created":"2023-05-11","cited_by_count":90},{"id":"2308.03279","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","created":"2023-08-07","cited_by_count":72},{"id":"1805.04174","title":"Joint Embedding of Words and Labels for Text Classification","created":"2018-05-10","cited_by_count":69},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49},{"id":"2010.15149","title":"Detecting Stance in Media on Global Warming","created":"2020-10-28","cited_by_count":48},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48},{"id":"2306.11559","title":"The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics","created":"2023-06-20","cited_by_count":46},{"id":"2206.02280","title":"Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future","created":"2022-06-05","cited_by_count":45},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41},{"id":"2211.07830","title":"Prompting Language Models for Linguistic Structure","created":"2022-11-15","cited_by_count":39},{"id":"1806.06219","title":"GILE: A Generalized Input-Label Embedding for Text Classification","created":"2018-06-16","cited_by_count":22},{"id":"2212.10405","title":"AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection","created":"2022-12-20","cited_by_count":12},{"id":"2212.10397","title":"Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization","created":"2022-12-20","cited_by_count":10},{"id":"2305.20045","title":"ActiveAED: A Human in the Loop Improves Annotation Error Detection","created":"2023-05-31","cited_by_count":9},{"id":"2402.03221","title":"\"Define Your Terms\" : Enhancing Efficient Offensive Speech Classification with Definition","created":"2024-02-05","cited_by_count":7},{"id":"2304.14599","title":"Antisemitic Messages? A Guide to High-Quality Annotation and a Labeled Dataset of Tweets","created":"2023-04-28","cited_by_count":6},{"id":"2305.18034","title":"A Corpus for Sentence-level Subjectivity Detection on English News Articles","created":"2023-05-29","cited_by_count":6},{"id":"1911.01026","title":"Metric Learning for Dynamic Text Classification","created":"2019-11-04","cited_by_count":5},{"id":"2110.00125","title":"Combining Transformers with Natural Language Explanations","created":"2021-09-02","cited_by_count":1}],"next_cursor":null}