{"list":"other","total":57,"rows":[{"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":"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"1810.10147","title":"FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation","created":"2018-10-24","cited_by_count":254},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2103.06268","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","created":"2021-03-10","cited_by_count":236},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2205.12689","title":"Large Language Models are Few-Shot Clinical Information Extractors","created":"2022-05-25","cited_by_count":207},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176},{"id":"2303.16854","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","created":"2023-03-29","cited_by_count":172},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"1710.06071","title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","created":"2017-10-17","cited_by_count":124},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"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":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72},{"id":"2303.03953","title":"ChatGPT: Beginning of an End of Manual Linguistic Data Annotation? Use Case of Automatic Genre Identification","created":"2023-03-07","cited_by_count":45},{"id":"1904.02181","title":"Probing Biomedical Embeddings from Language Models","created":"2019-04-03","cited_by_count":39},{"id":"1903.05844","title":"Learning Dependency Structures for Weak Supervision Models","created":"2019-03-14","cited_by_count":32},{"id":"1910.00216","title":"Revisiting Fine-tuning for Few-shot Learning","created":"2019-10-01","cited_by_count":29},{"id":"2112.03865","title":"Universalizing Weak Supervision","created":"2021-12-07","cited_by_count":27},{"id":"2206.02914","title":"Training Subset Selection for Weak Supervision","created":"2022-06-06","cited_by_count":19},{"id":"2203.13270","title":"Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision","created":"2022-03-24","cited_by_count":18},{"id":"2209.06120","title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","created":"2022-09-13","cited_by_count":17},{"id":"2207.13545","title":"Learning Hyper Label Model for Programmatic Weak Supervision","created":"2022-07-27","cited_by_count":16},{"id":"2211.13375","title":"Lifting Weak Supervision To Structured Prediction","created":"2022-11-24","cited_by_count":10},{"id":"2210.03594","title":"Label Propagation with Weak Supervision","created":"2022-10-07","cited_by_count":9},{"id":"1909.10724","title":"Situating Sentence Embedders with Nearest Neighbor Overlap","created":"2019-09-24","cited_by_count":3}],"next_cursor":null}