{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"2006.13114","title":"Fairness without Demographics through Adversarially Reweighted Learning","created":"2020-06-23","cited_by_count":251},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1811.04251","title":"Formal Limitations on the Measurement of Mutual Information","created":"2018-11-10","cited_by_count":189},{"id":"2005.00813","title":"Social Biases in NLP Models as Barriers for Persons with Disabilities","created":"2020-05-02","cited_by_count":182},{"id":"1808.06640","title":"Adversarial Removal of Demographic Attributes from Text Data","created":"2018-08-20","cited_by_count":170},{"id":"1707.00075","title":"Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations","created":"2017-07-01","cited_by_count":165},{"id":"1806.06055","title":"Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees","created":"2018-06-15","cited_by_count":146},{"id":"1905.13662","title":"On the Fairness of Disentangled Representations","created":"2019-05-31","cited_by_count":144},{"id":"1704.00805","title":"On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning","created":"2017-04-03","cited_by_count":142},{"id":"1911.01485","title":"Assessing Social and Intersectional Biases in Contextualized Word Representations","created":"2019-11-04","cited_by_count":135},{"id":"1907.12059","title":"Wasserstein Fair Classification","created":"2019-07-28","cited_by_count":131},{"id":"2207.07068","title":"Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey","created":"2022-07-14","cited_by_count":125},{"id":"1708.00524","title":"Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm","created":"2017-08-01","cited_by_count":118},{"id":"2012.01696","title":"FairBatch: Batch Selection for Model Fairness","created":"2020-12-03","cited_by_count":99},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75},{"id":"1903.11780","title":"Wasserstein Dependency Measure for Representation Learning","created":"2019-03-28","cited_by_count":69},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58},{"id":"1803.01541","title":"Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect","created":"2018-03-05","cited_by_count":49},{"id":"1906.03284","title":"Equalized odds postprocessing under imperfect group information","created":"2019-06-07","cited_by_count":48},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48},{"id":"2101.04108","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","created":"2021-01-11","cited_by_count":45},{"id":"2104.14537","title":"Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features","created":"2021-04-29","cited_by_count":45},{"id":"2003.00343","title":"Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation","created":"2020-02-29","cited_by_count":43},{"id":"2007.08259","title":"Transferable Calibration with Lower Bias and Variance in Domain Adaptation","created":"2020-07-16","cited_by_count":41},{"id":"1906.09688","title":"Transfer of Machine Learning Fairness across Domains","created":"2019-06-24","cited_by_count":36},{"id":"2010.16326","title":"All of the Fairness for Edge Prediction with Optimal Transport","created":"2020-10-30","cited_by_count":36},{"id":"2106.01963","title":"A Survey on Optimal Transport for Machine Learning: Theory and Applications","created":"2021-06-03","cited_by_count":35},{"id":"2109.08253","title":"Balancing out Bias: Achieving Fairness Through Balanced Training","created":"2021-09-16","cited_by_count":34},{"id":"1806.11212","title":"Proxy Fairness","created":"2018-06-28","cited_by_count":29},{"id":"2304.10153","title":"On the Independence of Association Bias and Empirical Fairness in Language Models","created":"2023-04-20","cited_by_count":29},{"id":"1710.04394","title":"Provably Fair Representations","created":"2017-10-12","cited_by_count":22},{"id":"2205.02393","title":"Optimising Equal Opportunity Fairness in Model Training","created":"2022-05-05","cited_by_count":22},{"id":"2110.03618","title":"Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP","created":"2021-10-07","cited_by_count":21},{"id":"1908.05783","title":"Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization","created":"2019-08-15","cited_by_count":18},{"id":"2207.05685","title":"PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners","created":"2022-07-12","cited_by_count":13},{"id":"2304.06537","title":"Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution","created":"2023-04-13","cited_by_count":12},{"id":"2302.05711","title":"Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP","created":"2023-02-11","cited_by_count":11},{"id":"2410.02028","title":"Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions","created":"2024-10-02","cited_by_count":11},{"id":"2204.04440","title":"Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks","created":"2022-04-09","cited_by_count":10},{"id":"2410.10476","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","created":"2024-10-14","cited_by_count":6},{"id":"2307.13081","title":"Fairness Under Demographic Scarce Regime","created":"2023-07-24","cited_by_count":4},{"id":"2311.12689","title":"Fair Text Classification with Wasserstein Independence","created":"2023-11-21","cited_by_count":4},{"id":"2403.09516","title":"Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information","created":"2024-03-14","cited_by_count":3},{"id":"2406.16738","title":"Inducing Group Fairness in Prompt-Based Language Model Decisions","created":"2024-06-24","cited_by_count":3},{"id":"2409.13705","title":"Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble","created":"2024-09-05","cited_by_count":3},{"id":"2410.10153","title":"Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?","created":"2024-10-14","cited_by_count":2},{"id":"2410.00179","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","created":"2024-09-30","cited_by_count":1}],"next_cursor":null}