Responsible AI

‘Beach’ to ‘Bitch’: Inadvertent Unsafe Transcription of Kids’ Content on YouTube AAAI 2022 Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media EMNLP 2022 Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models NeurIPS 2022 Consent as a Foundation for Responsible Autonomy AAAI 2022 Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation EMNLP 2022 Contextualizing Language Models for Norms Diverging from Social Majority EMNLP 2022 Controlling Bias Exposure for Fair Interpretable Predictions EMNLP 2022 Creating Interpretable Data-Driven Approaches for Tropical Cyclones Forecasting AAAI 2022 Cross-Domain Detection of GPT-2-Generated Technical Text NAACL 2022 Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks COLING 2022 Debiasing Masks: A New Framework for Shortcut Mitigation in NLU EMNLP 2022 Debiasing Pre-Trained Language Models via Efficient Fine-Tuning ACL 2022 DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding AAAI 2022 DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning NeurIPS 2022 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 Delivering Trustworthy AI through Formal XAI AAAI 2022 Demographic-Aware Language Model Fine-tuning as a Bias Mitigation Technique AACL 2022 Development and Validation of ML-DQA – a Machine Learning Data Quality Assurance Framework for Healthcare MLHC 2022 Differentially private multi-party data release for linear regression UAI 2022 Directions for NLP Practices Applied to Online Hate Speech Detection EMNLP 2022 Director: Generator-Classifiers For Supervised Language Modeling AACL 2022 Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning MLHC 2022 Does Representational Fairness Imply Empirical Fairness? AACL 2022 Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models EMNLP 2022 Efficient Counterfactual Debiasing for Visual Question Answering WACV 2022