Responsible AI

Implications of Model Indeterminacy for Explanations of Automated Decisions NeurIPS 2022 Improving Factual Consistency in Summarization with Compression-Based Post-Editing EMNLP 2022 Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards EMNLP 2022 “I’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset EMNLP 2022 In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning NeurIPS 2022 Is NLP Ready for Standardization? EMNLP 2022 Language Model Detoxification in Dialogue with Contextualized Stance Control EMNLP 2022 Large-Scale Differentially Private BERT EMNLP 2022 Local Differential Privacy Meets Computational Social Choice - Resilience under Voter Deletion IJCAI 2022 Local Justice and the Algorithmic Allocation of Scarce Societal Resources AAAI 2022 Longitudinal Fairness with Censorship AAAI 2022 Lost in Distillation: A Case Study in Toxicity Modeling NAACL 2022 Manipulating SHAP via Adversarial Data Perturbations (Student Abstract) AAAI 2022 Measure and Improve Robustness in NLP Models: A Survey NAACL 2022 Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals ACL 2022 Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models EMNLP 2022 Mitigating Covertly Unsafe Text within Natural Language Systems EMNLP 2022 Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy NAACL 2022 On Computing Probabilistic Explanations for Decision Trees NeurIPS 2022 One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia ACL 2022 On Facility Location Problem in the Local Differential Privacy Model AISTATS 2022 On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations ACL 2022 On the Machine Learning of Ethical Judgments from Natural Language NAACL 2022 Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next ACL 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022