Fairness

One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia ACL 2022 On Feature Learning in the Presence of Spurious Correlations NeurIPS 2022 On Gender Biases in Offensive Language Classification Models NAACL 2022 On Guiding Visual Attention With Language Specification CVPR 2022 On Improving Resource Allocations by Sharing AAAI 2022 On Learning Fairness and Accuracy on Multiple Subgroups NeurIPS 2022 On Measures of Biases and Harms in NLP AACL 2022 On Measuring Social Biases in Prompt-Based Multi-Task Learning NAACL 2022 On Testing for Discrimination Using Causal Models AAAI 2022 On the Adversarial Robustness of Causal Algorithmic Recourse ICML 2022 On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs NeurIPS 2022 On the Epistemic Limits of Personalized Prediction NeurIPS 2022 On the Fairness of Causal Algorithmic Recourse AAAI 2022 On the Impossibility of Non-trivial Accuracy in Presence of Fairness Constraints AAAI 2022 On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations ACL 2022 On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models? NAACL 2022 On the Relation between Distributionally Robust Optimization and Data Curation (Student Abstract) AAAI 2022 On the Tradeoff Between Robustness and Fairness NeurIPS 2022 OpenXAI: Towards a Transparent Evaluation of Model Explanations NeurIPS 2022 Opportunities for Human-centered Evaluation of Machine Translation Systems NAACL 2022 Optimal Efficiency-Envy Trade-Off via Optimal Transport NeurIPS 2022 Optimal Training of Fair Predictive Models CLeaR 2022 Optimal Transport of Classifiers to Fairness NeurIPS 2022 Optimising Equal Opportunity Fairness in Model Training NAACL 2022 Outlier-Aware Training for Improving Group Accuracy Disparities AACL 2022