{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1811.00995","title":"Invertible Residual Networks","created":"2018-11-02","cited_by_count":365},{"id":"1803.05449","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","created":"2018-03-14","cited_by_count":294},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"1704.03471","title":"What do Neural Machine Translation Models Learn about Morphology?","created":"2017-04-11","cited_by_count":166},{"id":"1903.03260","title":"Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State","created":"2019-03-08","cited_by_count":138},{"id":"2109.09193","title":"Towards Zero-Label Language Learning","created":"2021-09-19","cited_by_count":76},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50},{"id":"2005.00870","title":"Predicting Performance for Natural Language Processing Tasks","created":"2020-05-02","cited_by_count":49},{"id":"2106.03634","title":"PROST: Physical Reasoning of Objects through Space and Time","created":"2021-06-07","cited_by_count":48},{"id":"2106.08694","title":"On the proper role of linguistically-oriented deep net analysis in linguistic theorizing","created":"2021-06-16","cited_by_count":43},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42},{"id":"2005.01641","title":"A Tale of a Probe and a Parser","created":"2020-05-04","cited_by_count":40},{"id":"2010.02616","title":"On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers","created":"2020-10-06","cited_by_count":39},{"id":"2105.15179","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","created":"2021-05-31","cited_by_count":32},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26},{"id":"2202.12246","title":"Neural reality of argument structure constructions","created":"2022-02-24","cited_by_count":25},{"id":"2105.07452","title":"How is BERT surprised? Layerwise detection of linguistic anomalies","created":"2021-05-16","cited_by_count":24},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24},{"id":"2010.01869","title":"Linguistic Profiling of a Neural Language Model","created":"2020-10-05","cited_by_count":23},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22},{"id":"2009.07364","title":"An information theoretic view on selecting linguistic probes","created":"2020-09-15","cited_by_count":19},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14},{"id":"2202.00563","title":"On the Limitations of General Purpose Domain Generalisation Methods","created":"2022-02-01","cited_by_count":10},{"id":"1910.07485","title":"Excess risk bounds in robust empirical risk minimization","created":"2019-10-16","cited_by_count":9},{"id":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6},{"id":"2111.04260","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","created":"2021-11-08","cited_by_count":6},{"id":"2202.12801","title":"On the data requirements of probing","created":"2022-02-25","cited_by_count":4},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3}],"next_cursor":null}