{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1810.09136","title":"Do Deep Generative Models Know What They Don't Know?","created":"2018-10-22","cited_by_count":443},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"1802.00393","title":"Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior","created":"2018-02-01","cited_by_count":270},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"1908.07086","title":"Human uncertainty makes classification more robust","created":"2019-08-19","cited_by_count":235},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"1910.04851","title":"Addressing Failure Prediction by Learning Model Confidence","created":"2019-10-01","cited_by_count":186},{"id":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"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":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139},{"id":"2109.04270","title":"Toward a Perspectivist Turn in Ground Truthing for Predictive Computing","created":"2021-09-09","cited_by_count":130},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"1709.01779","title":"Deep learning from crowds","created":"2017-09-06","cited_by_count":105},{"id":"1703.08774","title":"Who Said What: Modeling Individual Labelers Improves Classification","created":"2017-03-26","cited_by_count":77},{"id":"2109.13563","title":"Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement","created":"2021-09-28","cited_by_count":72},{"id":"2210.16133","title":"Stop Measuring Calibration When Humans Disagree","created":"2022-10-28","cited_by_count":71},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"2109.14591","title":"Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration","created":"2021-09-29","cited_by_count":40},{"id":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39},{"id":"1904.04792","title":"Quizbowl: The Case for Incremental Question Answering","created":"2019-04-09","cited_by_count":36},{"id":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31},{"id":"1808.06080","title":"CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement","created":"2018-08-18","cited_by_count":27},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20},{"id":"2206.15455","title":"Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions","created":"2022-06-30","cited_by_count":18},{"id":"2311.05265","title":"Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels","created":"2023-11-09","cited_by_count":17}],"next_cursor":null}