{"list":"other","total":122,"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":"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"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":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"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":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"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":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"1606.04586","title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning","created":"2016-06-14","cited_by_count":441},{"id":"1511.05547","title":"Return of Frustratingly Easy Domain Adaptation","created":"2015-11-17","cited_by_count":391},{"id":"1908.10063","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","created":"2019-08-27","cited_by_count":385},{"id":"1511.05644","title":"Adversarial Autoencoders","created":"2015-11-18","cited_by_count":364},{"id":"2003.00104","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","created":"2020-02-28","cited_by_count":362},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"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":"2002.11361","title":"Understanding Self-Training for Gradual Domain Adaptation","created":"2020-02-26","cited_by_count":149},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"2003.08607","title":"Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering","created":"2020-03-19","cited_by_count":140},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130},{"id":"2103.03571","title":"Cycle Self-Training for Domain Adaptation","created":"2021-03-05","cited_by_count":120},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115},{"id":"1907.05774","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","created":"2019-07-12","cited_by_count":110},{"id":"2105.10311","title":"Pretrained Language Models for Text Generation: A Survey","created":"2021-05-21","cited_by_count":95},{"id":"1803.09210","title":"Importance Weighted Adversarial Nets for Partial Domain Adaptation","created":"2018-03-25","cited_by_count":90},{"id":"1607.00485","title":"Group Sparse Regularization for Deep Neural Networks","created":"2016-07-02","cited_by_count":89},{"id":"1904.04402","title":"Towards Universal Object Detection by Domain Attention","created":"2019-04-09","cited_by_count":89},{"id":"1903.12230","title":"Learning to Transfer Examples for Partial Domain Adaptation","created":"2019-03-28","cited_by_count":87},{"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":"2010.03546","title":"Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing","created":"2020-10-07","cited_by_count":72},{"id":"1911.12983","title":"Correlation-aware Adversarial Domain Adaptation and Generalization","created":"2019-11-29","cited_by_count":65},{"id":"2001.01046","title":"Adversarial-Learned Loss for Domain Adaptation","created":"2020-01-04","cited_by_count":65},{"id":"1908.11860","title":"Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification","created":"2019-08-30","cited_by_count":63},{"id":"2103.11332","title":"AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization","created":"2021-03-21","cited_by_count":51},{"id":"1912.08954","title":"An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation","created":"2019-12-18","cited_by_count":48},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46},{"id":"1701.07275","title":"Universal representations:The missing link between faces, text, planktons, and cat breeds","created":"2017-01-25","cited_by_count":45},{"id":"1809.00068","title":"Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection","created":"2018-08-31","cited_by_count":43},{"id":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40},{"id":"2106.08062","title":"SSMix: Saliency-Based Span Mixup for Text Classification","created":"2021-06-15","cited_by_count":39},{"id":"1606.02892","title":"Linguistic Input Features Improve Neural Machine Translation","created":"2016-06-09","cited_by_count":38},{"id":"2106.13474","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","created":"2021-06-25","cited_by_count":36},{"id":"2109.07460","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","created":"2021-09-15","cited_by_count":34},{"id":"1708.00712","title":"Dynamic Data Selection for Neural Machine Translation","created":"2017-08-02","cited_by_count":33},{"id":"2104.07078","title":"UDALM: Unsupervised Domain Adaptation through Language Modeling","created":"2021-04-14","cited_by_count":33},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32},{"id":"1912.11975","title":"Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation","created":"2019-12-27","cited_by_count":30},{"id":"1805.01817","title":"Extreme Adaptation for Personalized Neural Machine Translation","created":"2018-05-04","cited_by_count":27},{"id":"2106.11575","title":"Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering","created":"2021-06-22","cited_by_count":27},{"id":"2010.05904","title":"Multi-Stage Pre-training for Low-Resource Domain Adaptation","created":"2020-10-12","cited_by_count":24},{"id":"2011.11499","title":"Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model","created":"2020-11-23","cited_by_count":24},{"id":"2103.02205","title":"Gradual Fine-Tuning for Low-Resource Domain Adaptation","created":"2021-03-03","cited_by_count":24},{"id":"2004.03354","title":"Inexpensive Domain Adaptation of Pretrained Language Models: Case Studies on Biomedical NER and Covid-19 QA","created":"2020-04-07","cited_by_count":23},{"id":"2009.07806","title":"Transformer Based Multi-Source Domain Adaptation","created":"2020-09-16","cited_by_count":23},{"id":"1910.09342","title":"Domain-agnostic Question-Answering with Adversarial Training","created":"2019-10-21","cited_by_count":22},{"id":"1908.09209","title":"Adversarial Domain Adaptation for Machine Reading Comprehension","created":"2019-08-24","cited_by_count":21}],"next_cursor":"100"}