Fairness

Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language Models ACL 2022 Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees NeurIPS 2022 Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View ACL 2022 Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models EMNLP 2022 Causal Conceptions of Fairness and their Consequences ICML 2022 Causal Explanations and XAI CLeaR 2022 Certifying Some Distributional Fairness with Subpopulation Decomposition NeurIPS 2022 Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models NAACL 2022 Challenges in Measuring Bias via Open-Ended Language Generation NAACL 2022 Classification without (Proper) Representation: Political Heterogeneity in Social Media and Its Implications for Classification and Behavioral Analysis ACL 2022 Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness (Extended Abstract) IJCAI 2022 Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off NeurIPS 2022 Conditional Supervised Contrastive Learning for Fair Text Classification EMNLP 2022 Conformalized Fairness via Quantile Regression NeurIPS 2022 Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions NeurIPS 2022 Contextual Debiasing for Visual Recognition With Causal Mechanisms CVPR 2022 Controllable Text Generation for Open-Domain Creativity and Fairness IJCAI 2022 Controlling Bias Exposure for Fair Interpretable Predictions EMNLP 2022 Controlling Directions Orthogonal to a Classifier ICLR 2022 Controlling for Stereotypes in Multimodal Language Model Evaluation EMNLP 2022 Conversational Inequality Through the Lens of Political Interruption IJCAI 2022 Cooperative Multi-Agent Fairness and Equivariant Policies AAAI 2022 Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists ACL 2022 Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations ICML 2022 Counterfactual Fairness with Partially Known Causal Graph NeurIPS 2022