{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"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":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"1909.07606","title":"K-BERT: Enabling Language Representation with Knowledge Graph","created":"2019-09-17","cited_by_count":304},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1909.04164","title":"Knowledge Enhanced Contextual Word Representations","created":"2019-09-09","cited_by_count":296},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2012.00363","title":"Modifying Memories in Transformer Models","created":"2020-12-01","cited_by_count":224},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132},{"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":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"1912.09637","title":"Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model","created":"2019-12-20","cited_by_count":102},{"id":"1901.11373","title":"Learning and Evaluating General Linguistic Intelligence","created":"2019-01-31","cited_by_count":79},{"id":"1908.05646","title":"SenseBERT: Driving Some Sense into BERT","created":"2019-08-15","cited_by_count":73},{"id":"1911.00720","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","created":"2019-11-02","cited_by_count":35},{"id":"2210.05549","title":"Continual Training of Language Models for Few-Shot Learning","created":"2022-10-11","cited_by_count":33},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23},{"id":"2104.08145","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","created":"2021-04-09","cited_by_count":11},{"id":"2010.02569","title":"StyleDGPT: Stylized Response Generation with Pre-trained Language Models","created":"2020-10-06","cited_by_count":10}],"next_cursor":null}