Fairness

Less Is Better: Recovering Intended-Feature Subspace to Robustify NLU Models COLING 2022 Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers CVPR 2022 Linear Adversarial Concept Erasure ICML 2022 Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ACL 2022 LITMUS Predictor: An AI Assistant for Building Reliable, High-Performing and Fair Multilingual NLP Systems AAAI 2022 Local calibration: metrics and recalibration UAI 2022 Local Justice and the Algorithmic Allocation of Scarce Societal Resources AAAI 2022 Longitudinal Fairness with Censorship AAAI 2022 Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference EMNLP 2022 Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements NAACL 2022 Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering EMNLP 2022 Low-Degree Multicalibration COLT 2022 MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining ICLR 2022 Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic ACL 2022 Margin-distancing for safe model explanation AISTATS 2022 Market Design for Drone Traffic Management AAAI 2022 MaskTune: Mitigating Spurious Correlations by Forcing to Explore NeurIPS 2022 Matching Learned Causal Effects of Neural Networks with Domain Priors ICML 2022 Measure and Improve Robustness in NLP Models: A Survey NAACL 2022 Measuring and Mitigating Name Biases in Neural Machine Translation ACL 2022 Measuring Fairness of Text Classifiers via Prediction Sensitivity ACL 2022 Measuring Geographic Performance Disparities of Offensive Language Classifiers COLING 2022 Measuring Harmful Representations in Scandinavian Language Models EMNLP 2022 Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals ACL 2022 Measuring Hidden Bias Within Face Recognition via Racial Phenotypes WACV 2022