{"list":"other","total":100,"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"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":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2010.03532","title":"What Can We Learn from Collective Human Opinions on Natural Language Inference Data?","created":"2020-10-07","cited_by_count":153},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"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":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","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":"2004.14444","title":"The Effect of Natural Distribution Shift on Question Answering Models","created":"2020-04-29","cited_by_count":104},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91},{"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":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"1905.13453","title":"MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension","created":"2019-05-31","cited_by_count":60},{"id":"2104.07644","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","created":"2021-04-15","cited_by_count":58},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57},{"id":"1806.00358","title":"A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset","created":"2018-06-01","cited_by_count":55},{"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":"2104.10097","title":"Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing","created":"2021-04-20","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":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47},{"id":"2007.04792","title":"Targeting the Benchmark: On Methodology in Current Natural Language Processing Research","created":"2020-07-07","cited_by_count":45},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","cited_by_count":44},{"id":"2007.14435","title":"Towards Ecologically Valid Research on Language User Interfaces","created":"2020-07-28","cited_by_count":42},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38},{"id":"1910.04601","title":"R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason","created":"2019-10-10","cited_by_count":36},{"id":"1611.00601","title":"Ordinal Common-sense Inference","created":"2016-11-02","cited_by_count":35},{"id":"1909.03042","title":"Uncertain Natural Language Inference","created":"2019-09-06","cited_by_count":35},{"id":"2005.01525","title":"To Test Machine Comprehension, Start by Defining Comprehension","created":"2020-05-04","cited_by_count":31},{"id":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","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":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29},{"id":"2209.03392","title":"Investigating Reasons for Disagreement in Natural Language Inference","created":"2022-09-07","cited_by_count":29},{"id":"2010.10418","title":"ConjNLI: Natural Language Inference Over Conjunctive Sentences","created":"2020-10-20","cited_by_count":27},{"id":"2103.06944","title":"Preregistering NLP Research","created":"2021-03-11","cited_by_count":25},{"id":"1711.01505","title":"Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task","created":"2017-11-04","cited_by_count":24},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23},{"id":"2106.03020","title":"Embracing Ambiguity: Shifting the Training Target of NLI Models","created":"2021-06-06","cited_by_count":23},{"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":"1910.14464","title":"What Question Answering can Learn from Trivia Nerds","created":"2019-10-31","cited_by_count":21},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19},{"id":"2003.04642","title":"A Framework for Evaluation of Machine Reading Comprehension Gold Standards","created":"2020-03-10","cited_by_count":18},{"id":"2102.04310","title":"The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point","created":"2021-02-08","cited_by_count":12},{"id":"2105.12762","title":"Quantifying and Avoiding Unfair Qualification Labour in Crowdsourcing","created":"2021-05-26","cited_by_count":11},{"id":"1911.03850","title":"Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses","created":"2019-11-10","cited_by_count":8},{"id":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4}],"next_cursor":null}