{"list":"other","total":78,"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":"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"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":"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":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"2206.08452","title":"GOOD: A Graph Out-of-Distribution Benchmark","created":"2022-06-16","cited_by_count":141},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"1702.03814","title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","created":"2017-02-13","cited_by_count":121},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101},{"id":"1808.04926","title":"How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks","created":"2018-08-14","cited_by_count":88},{"id":"1906.02900","title":"Compositional Questions Do Not Necessitate Multi-hop Reasoning","created":"2019-06-07","cited_by_count":88},{"id":"2109.06827","title":"Types of Out-of-Distribution Texts and How to Detect Them","created":"2021-09-14","cited_by_count":80},{"id":"2012.10040","title":"Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals","created":"2020-12-18","cited_by_count":67},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2010.02114","title":"Explaining The Efficacy of Counterfactually Augmented Data","created":"2020-10-05","cited_by_count":65},{"id":"1909.03862","title":"Out-of-domain Detection for Natural Language Understanding in Dialog Systems","created":"2019-09-09","cited_by_count":62},{"id":"2007.06661","title":"Robustness to Spurious Correlations via Human Annotations","created":"2020-07-13","cited_by_count":62},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41},{"id":"2010.12512","title":"Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification","created":"2020-10-23","cited_by_count":40},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30},{"id":"2202.04824","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","created":"2022-02-10","cited_by_count":30},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30},{"id":"2203.12918","title":"A Rationale-Centric Framework for Human-in-the-loop Machine Learning","created":"2022-03-24","cited_by_count":27},{"id":"2210.12365","title":"NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation","created":"2022-10-22","cited_by_count":23},{"id":"2106.14464","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","created":"2021-06-28","cited_by_count":22},{"id":"2109.12742","title":"FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding","created":"2021-09-27","cited_by_count":17},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16},{"id":"2210.13604","title":"The Robustness Limits of SoTA Vision Models to Natural Variation","created":"2022-10-24","cited_by_count":15},{"id":"2203.08788","title":"Are Shortest Rationales the Best Explanations for Human Understanding?","created":"2022-03-16","cited_by_count":8},{"id":"2208.11464","title":"FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition","created":"2022-08-24","cited_by_count":7},{"id":"2209.03834","title":"Pre-Training a Graph Recurrent Network for Language Representation","created":"2022-09-08","cited_by_count":1}],"next_cursor":null}