{"list":"other","total":66,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"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":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"1701.08230","title":"Algorithmic decision making and the cost of fairness","created":"2017-01-28","cited_by_count":403},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"1708.02862","title":"WebVision Database: Visual Learning and Understanding from Web Data","created":"2017-08-09","cited_by_count":262},{"id":"2001.10528","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","created":"2020-01-28","cited_by_count":261},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"1903.12394","title":"Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems","created":"2019-03-29","cited_by_count":205},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"id":"1511.05897","title":"Censoring Representations with an Adversary","created":"2015-11-18","cited_by_count":192},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2011.01821","title":"Minimax Pareto Fairness: A Multi Objective Perspective","created":"2020-11-03","cited_by_count":153},{"id":"1810.08810","title":"The Frontiers of Fairness in Machine Learning","created":"2018-10-20","cited_by_count":141},{"id":"1912.11078","title":"Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview","created":"2019-11-09","cited_by_count":137},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"2106.00467","title":"A Clarification of the Nuances in the Fairness Metrics Landscape","created":"2021-06-01","cited_by_count":98},{"id":"1810.09821","title":"Self-Erasing Network for Integral Object Attention","created":"2018-10-23","cited_by_count":95},{"id":"2007.13019","title":"Feedback Loop and Bias Amplification in Recommender Systems","created":"2020-07-25","cited_by_count":90},{"id":"1901.07555","title":"Managing Popularity Bias in Recommender Systems with Personalized Re-ranking","created":"2019-01-22","cited_by_count":82},{"id":"1601.05764","title":"A Confidence-Based Approach for Balancing Fairness and Accuracy","created":"2016-01-21","cited_by_count":73},{"id":"1907.13286","title":"The Unfairness of Popularity Bias in Recommendation","created":"2019-07-31","cited_by_count":70},{"id":"2007.06570","title":"Towards causal benchmarking of bias in face analysis algorithms","created":"2020-07-13","cited_by_count":64},{"id":"2111.02447","title":"On the Frequency Bias of Generative Models","created":"2021-11-03","cited_by_count":60},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60},{"id":"2101.04108","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","created":"2021-01-11","cited_by_count":45},{"id":"1610.08077","title":"A statistical framework for fair predictive algorithms","created":"2016-10-25","cited_by_count":38},{"id":"2003.06975","title":"TACO: Trash Annotations in Context for Litter Detection","created":"2020-03-16","cited_by_count":38},{"id":"2010.01473","title":"Spatial Frequency Bias in Convolutional Generative Adversarial Networks","created":"2020-10-04","cited_by_count":35},{"id":"2107.04782","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","created":"2021-07-10","cited_by_count":35},{"id":"1807.07532","title":"Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs","created":"2018-07-19","cited_by_count":32},{"id":"1904.08818","title":"(De)Constructing Bias on Skin Lesion Datasets","created":"2019-04-18","cited_by_count":30},{"id":"2105.14150","title":"Annotation Inconsistency and Entity Bias in MultiWOZ","created":"2021-05-29","cited_by_count":30},{"id":"1804.02969","title":"A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models","created":"2018-04-09","cited_by_count":22},{"id":"1707.00574","title":"How algorithmic popularity bias hinders or promotes quality","created":"2017-07-03","cited_by_count":20},{"id":"1911.04931","title":"Efficient Fair Principal Component Analysis","created":"2019-11-12","cited_by_count":20},{"id":"1304.0564","title":"On the definition of a confounder","created":"2013-04-02","cited_by_count":19},{"id":"2005.09379","title":"Staying True to Your Word: (How) Can Attention Become Explanation?","created":"2020-05-19","cited_by_count":18},{"id":"2308.04346","title":"Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles","created":"2023-08-08","cited_by_count":16},{"id":"1803.01316","title":"On Cognitive Preferences and the Plausibility of Rule-based Models","created":"2018-03-04","cited_by_count":14},{"id":"1709.04347","title":"Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection","created":"2017-09-13","cited_by_count":13},{"id":"2109.04374","title":"IFBiD: Inference-Free Bias Detection","created":"2021-09-09","cited_by_count":11},{"id":"2206.11423","title":"Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing","created":"2022-06-22","cited_by_count":11},{"id":"2206.15182","title":"The (de)biasing effect of GAN-based augmentation methods on skin lesion images","created":"2022-06-30","cited_by_count":9},{"id":"2101.08698","title":"Validating Label Consistency in NER Data Annotation","created":"2021-01-21","cited_by_count":7},{"id":"2111.00814","title":"Statistical quantification of confounding bias in predictive modelling","created":"2021-11-01","cited_by_count":7},{"id":"1710.04924","title":"Two-stage Algorithm for Fairness-aware Machine Learning","created":"2017-10-13","cited_by_count":6},{"id":"2107.00360","title":"Towards Measuring Bias in Image Classification","created":"2021-07-01","cited_by_count":6},{"id":"2204.00536","title":"Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder","created":"2022-04-01","cited_by_count":5},{"id":"1703.01671","title":"Controlling for Unobserved Confounds in Classification Using Correlational Constraints","created":"2017-03-05","cited_by_count":2},{"id":"2308.09464","title":"Data augmentation and explainability for bias discovery and mitigation in deep learning","created":"2023-08-18","cited_by_count":2}],"next_cursor":null}