{"list":"other","total":75,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"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":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1909.08072","title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","created":"2019-09-17","cited_by_count":237},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"1803.05567","title":"Achieving Human Parity on Automatic Chinese to English News Translation","created":"2018-03-15","cited_by_count":119},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"1909.02209","title":"Semantics-aware BERT for Language Understanding","created":"2019-09-05","cited_by_count":112},{"id":"2004.08994","title":"Adversarial Training for Large Neural Language Models","created":"2020-04-20","cited_by_count":111},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"1808.07048","title":"Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation","created":"2018-08-21","cited_by_count":88},{"id":"2004.14174","title":"Reevaluating Adversarial Examples in Natural Language","created":"2020-04-25","cited_by_count":85},{"id":"2005.00315","title":"Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance","created":"2020-05-01","cited_by_count":85},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64},{"id":"1808.10432","title":"Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation","created":"2018-08-30","cited_by_count":58},{"id":"2104.10809","title":"Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?","created":"2021-04-22","cited_by_count":55},{"id":"1811.00731","title":"The age of secrecy and unfairness in recidivism prediction","created":"2018-11-02","cited_by_count":53},{"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":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51},{"id":"1906.08069","title":"The Effect of Translationese in Machine Translation Test Sets","created":"2019-06-19","cited_by_count":49},{"id":"1705.08807","title":"When Will AI Exceed Human Performance? Evidence from AI Experts","created":"2017-05-24","cited_by_count":41},{"id":"2010.12729","title":"ANLIzing the Adversarial Natural Language Inference Dataset","created":"2020-10-24","cited_by_count":36},{"id":"2104.04128","title":"An Empirical Comparison of Instance Attribution Methods for NLP","created":"2021-04-09","cited_by_count":35},{"id":"2006.04948","title":"AI Research Considerations for Human Existential Safety (ARCHES)","created":"2020-05-30","cited_by_count":33},{"id":"2010.03863","title":"What Can We Do to Improve Peer Review in NLP?","created":"2020-10-08","cited_by_count":32},{"id":"2105.10185","title":"A Non-Linear Structural Probe","created":"2021-05-21","cited_by_count":31},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31},{"id":"2001.09773","title":"Algorithmic Fairness from a Non-ideal Perspective","created":"2020-01-08","cited_by_count":30},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","cited_by_count":30},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28},{"id":"2004.12864","title":"DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking","created":"2020-04-27","cited_by_count":26},{"id":"2103.06944","title":"Preregistering NLP Research","created":"2021-03-11","cited_by_count":25},{"id":"2004.13606","title":"The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions","created":"2020-04-28","cited_by_count":22},{"id":"1609.05284","title":"ReasoNet: Learning to Stop Reading in Machine Comprehension","created":"2016-09-17","cited_by_count":21},{"id":"2106.02359","title":"How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact","created":"2021-06-04","cited_by_count":18},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14},{"id":"1911.01875","title":"Metrology for AI: From Benchmarks to Instruments","created":"2019-11-05","cited_by_count":12},{"id":"2109.07403","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","created":"2021-09-15","cited_by_count":9},{"id":"2110.02054","title":"NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models","created":"2021-08-29","cited_by_count":1}],"next_cursor":null}