Fairness

Trading-off price for data quality to achieve fair online allocation NeurIPS 2023 Trustworthy Policy Learning under the Counterfactual No-Harm Criterion ICML 2023 Unbiased Scene Graph Generation in Videos CVPR 2023 Unbiased Supervised Contrastive Learning ICLR 2023 Uncovering and Quantifying Social Biases in Code Generation NeurIPS 2023 Uncurated Image-Text Datasets: Shedding Light on Demographic Bias CVPR 2023 Understanding and Improving Ensemble Adversarial Defense NeurIPS 2023 Understanding the Effect of Model Compression on Social Bias in Large Language Models EMNLP 2023 Understanding the Impact of Adversarial Robustness on Accuracy Disparity ICML 2023 Unfooling Perturbation-Based Post Hoc Explainers AAAI 2023 Unlearning Bias in Language Models by Partitioning Gradients ACL 2023 Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance EMNLP 2023 Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach EMNLP 2023 User-Centric Democratization towards Social Value Aligned Medical AI Services IJCAI 2023 Using Liquid Democracy For Attention-Aware Social Choice IJCAI 2023 Variable-Based Calibration for Machine Learning Classifiers AAAI 2023 Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive EMNLP 2023 Vocoder drift in x-vector–based speaker anonymization Interspeech 2023 WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts NeurIPS 2023 Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes ICML 2023 When and Why Does Bias Mitigation Work? EMNLP 2023 When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset ACL 2023 When do Minimax-fair Learning and Empirical Risk Minimization Coincide? ICML 2023 When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization EACL 2023 When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations MLHC 2023