Fairness

Probably Approximate Shapley Fairness with Applications in Machine Learning AAAI 2023 Promoting Fairness in Classification of Quality of Medical Evidence ACL 2023 Proportionality in Approval-Based Participatory Budgeting AAAI 2023 Provable Detection of Propagating Sampling Bias in Prediction Models AAAI 2023 Provably Invariant Learning without Domain Information ICML 2023 Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play ICLR 2023 Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics ICLR 2023 Quantifying the Dialect Gap and its Correlates Across Languages EMNLP 2023 Race, Gender, and Age Biases in Biomedical Masked Language Models ACL 2023 Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization ICLR 2023 ROBBIE: Robust Bias Evaluation of Large Generative Language Models EMNLP 2023 Run Like a Girl! Sport-Related Gender Bias in Language and Vision ACL 2023 SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models ACL 2023 Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection ACL 2023 Social Bias Meets Data Bias: The Impacts of Labeling and Measurement Errors on Fairness Criteria AAAI 2023 Social-Group-Agnostic Bias Mitigation via the Stereotype Content Model ACL 2023 SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models EACL 2023 SSS at SemEval-2023 Task 10: Explainable Detection of Online Sexism using Majority Voted Fine-Tuned Transformers SemEval 2023 Statistically Profiling Biases in Natural Language Reasoning Datasets and Models EMNLP 2023 Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models ACL 2023 Stochastic Differentially Private and Fair Learning ICLR 2023 Stubborn Lexical Bias in Data and Models ACL 2023 Superhuman Fairness ICML 2023 Taxonomizing and Measuring Representational Harms: A Look at Image Tagging AAAI 2023 The Many Faces of Adversarial Machine Learning AAAI 2023