protected attribute

Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification EMNLP 2025 Evaluating Shortcut Utilization in Deep Learning Disease Classification through Counterfactual Analysis MIDL 2025 Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness ICML 2025 FairPFN: A Tabular Foundation Model for Causal Fairness ICML 2025 The cost of local and global fairness in Federated Learning AISTATS 2025 “The dentist is an involved parent, the bartender is not”: Revealing Implicit Biases in QA with Implicit BBQ AACL 2025 Fairness without Demographics through Shared Latent Space-Based Debiasing AAAI 2024 ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment AAAI 2024 Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection ACL 2023 Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks NeurIPS 2022 Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection EMNLP 2022 Bounding and Approximating Intersectional Fairness through Marginal Fairness NeurIPS 2022 Fairness Trade-Offs and Partial Debiasing ACML 2022 Fair Ranking with Noisy Protected Attributes NeurIPS 2022 Quantifying Societal Bias Amplification in Image Captioning CVPR 2022 Directional Bias Amplification ICML 2021 Evaluation of Summarization Systems across Gender, Age, and Race EMNLP 2021 Fair Classification with Adversarial Perturbations NeurIPS 2021 Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees ICML 2021 The Effect of Round-Trip Translation on Fairness in Sentiment Analysis EMNLP 2021 Deep Fair Clustering for Visual Learning CVPR 2020 Equalized odds postprocessing under imperfect group information AISTATS 2020 Fair Learning with Private Demographic Data ICML 2020 Fair Regression: Quantitative Definitions and Reduction-Based Algorithms ICML 2019 What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes NAACL 2019