{"list":"other","total":59,"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"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":"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":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"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":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"1612.01939","title":"Correlation Alignment for Unsupervised Domain Adaptation","created":"2016-12-06","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":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141},{"id":"2202.08005","title":"Should You Mask 15% in Masked Language Modeling?","created":"2022-02-16","cited_by_count":118},{"id":"1909.11825","title":"Unsupervised Domain Adaptation through Self-Supervision","created":"2019-09-26","cited_by_count":116},{"id":"2204.00570","title":"Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-04-01","cited_by_count":67},{"id":"1707.05246","title":"Learning to select data for transfer learning with Bayesian Optimization","created":"2017-07-17","cited_by_count":64},{"id":"2010.01825","title":"PMI-Masking: Principled masking of correlated spans","created":"2020-10-05","cited_by_count":54},{"id":"2011.03274","title":"Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data","created":"2020-11-06","cited_by_count":52},{"id":"2004.09733","title":"Train No Evil: Selective Masking for Task-Guided Pre-Training","created":"2020-04-21","cited_by_count":36},{"id":"2006.09075","title":"PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models","created":"2020-06-16","cited_by_count":33},{"id":"2104.07078","title":"UDALM: Unsupervised Domain Adaptation through Language Modeling","created":"2021-04-14","cited_by_count":33},{"id":"2001.04362","title":"Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits","created":"2020-01-13","cited_by_count":30},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29},{"id":"2010.12198","title":"Domain Divergences: a Survey and Empirical Analysis","created":"2020-10-23","cited_by_count":24},{"id":"2103.00751","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","created":"2021-03-01","cited_by_count":24},{"id":"2210.02952","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","created":"2022-10-06","cited_by_count":15},{"id":"2306.02767","title":"Cross-Lingual Transfer with Target Language-Ready Task Adapters","created":"2023-06-05","cited_by_count":15},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14},{"id":"2302.03194","title":"UDApter -- Efficient Domain Adaptation Using Adapters","created":"2023-02-07","cited_by_count":13},{"id":"2305.12717","title":"TADA: Efficient Task-Agnostic Domain Adaptation for Transformers","created":"2023-05-22","cited_by_count":6},{"id":"2311.09661","title":"Evolving Domain Adaptation of Pretrained Language Models for Text Classification","created":"2023-11-16","cited_by_count":5},{"id":"2207.04564","title":"Domain Confused Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-07-10","cited_by_count":4}],"next_cursor":null}