Responsible AI

What Do NLP Researchers Believe? Results of the NLP Community Metasurvey ACL 2023 When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks EMNLP 2023 Whose Opinions Do Language Models Reflect? ICML 2023 Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously Interspeech 2023 WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models ACL 2023 Xaitk-Saliency: An Open Source Explainable AI Toolkit for Saliency AAAI 2023 Actionable Model-Centric Explanations (Student Abstract) AAAI 2022 A Dataset for Efforts Towards Achieving the Sustainable Development Goal of Safe Working Environments NeurIPS 2022 AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis ICLR 2022 AI Explainability 360: Impact and Design AAAI 2022 Aligning Generative Language Models with Human Values NAACL 2022 Aligning to Social Norms and Values in Interactive Narratives NAACL 2022 A Major Obstacle for NLP Research: Let’s Talk about Time Allocation! EMNLP 2022 Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT System EMNLP 2022 Analyzing the Limits of Self-Supervision in Handling Bias in Language EMNLP 2022 An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models ACL 2022 An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models NAACL 2022 An Investigation of Critical Issues in Bias Mitigation Techniques WACV 2022 Are Large Pre-Trained Language Models Leaking Your Personal Information? EMNLP 2022 A Robust Bias Mitigation Procedure Based on the Stereotype Content Model EMNLP 2022 A Study of Implicit Bias in Pretrained Language Models against People with Disabilities COLING 2022 A Study on the Distribution of Social Biases in Self-Supervised Learning Visual Models CVPR 2022 A Survey on Stance Detection for Mis- and Disinformation Identification NAACL 2022 Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts ACL 2022 Balancing out Bias: Achieving Fairness Through Balanced Training EMNLP 2022