{"list":"other","total":53,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"1605.07723","title":"Data Programming: Creating Large Training Sets, Quickly","created":"2016-05-25","cited_by_count":246},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"1810.02840","title":"Training Complex Models with Multi-Task Weak Supervision","created":"2018-10-05","cited_by_count":106},{"id":"2002.11955","title":"Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods","created":"2020-02-27","cited_by_count":98},{"id":"2109.11377","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","created":"2021-09-23","cited_by_count":96},{"id":"2010.07835","title":"Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach","created":"2020-10-15","cited_by_count":83},{"id":"2205.00049","title":"Prompt Consistency for Zero-Shot Task Generalization","created":"2022-04-29","cited_by_count":67},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66},{"id":"2202.05144","title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","created":"2022-02-10","cited_by_count":62},{"id":"2203.09101","title":"RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction","created":"2022-03-17","cited_by_count":60},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54},{"id":"1812.00417","title":"Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale","created":"2018-12-02","cited_by_count":52},{"id":"1703.00854","title":"Learning the Structure of Generative Models without Labeled Data","created":"2017-03-02","cited_by_count":50},{"id":"2104.05514","title":"Self-Training with Weak Supervision","created":"2021-04-12","cited_by_count":49},{"id":"1903.05844","title":"Learning Dependency Structures for Weak Supervision Models","created":"2019-03-14","cited_by_count":32},{"id":"1903.11101","title":"Cross-Modal Data Programming Enables Rapid Medical Machine Learning","created":"2019-03-26","cited_by_count":32},{"id":"2112.03865","title":"Universalizing Weak Supervision","created":"2021-12-07","cited_by_count":27},{"id":"2202.00828","title":"Co-training Improves Prompt-based Learning for Large Language Models","created":"2022-02-02","cited_by_count":24},{"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":"2203.13270","title":"Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision","created":"2022-03-24","cited_by_count":18},{"id":"1910.09505","title":"Multi-Resolution Weak Supervision for Sequential Data","created":"2019-10-21","cited_by_count":17},{"id":"2106.04530","title":"Learning from Multiple Noisy Partial Labelers","created":"2021-06-08","cited_by_count":14},{"id":"2110.03484","title":"Creating Training Sets via Weak Indirect Supervision","created":"2021-10-07","cited_by_count":14},{"id":"2104.14847","title":"Active WeaSuL: Improving Weak Supervision with Active Learning","created":"2021-04-30","cited_by_count":12},{"id":"2009.07360","title":"Constrained Labeling for Weakly Supervised Learning","created":"2020-09-15","cited_by_count":10},{"id":"2001.07100","title":"Active and Incremental Learning with Weak Supervision","created":"2020-01-20","cited_by_count":8},{"id":"2008.09983","title":"Leveraging Organizational Resources to Adapt Models to New Data Modalities","created":"2020-08-23","cited_by_count":6},{"id":"1610.08123","title":"Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data","created":"2016-10-25","cited_by_count":3},{"id":"1904.07640","title":"Medical device surveillance with electronic health records","created":"2019-04-03","cited_by_count":3}],"next_cursor":null}