Responsible AI

Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLP ACL 2023 Norm Deviation in Multiagent Systems: A Foundation for Responsible Autonomy IJCAI 2023 Not The End of Story: An Evaluation of ChatGPT-Driven Vulnerability Description Mappings ACL 2023 On Measuring Fairness in Generative Models NeurIPS 2023 On Provable Copyright Protection for Generative Models ICML 2023 On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning ACL 2023 On the Exploitability of Instruction Tuning NeurIPS 2023 On The Real-world Performance of Machine Translation: Exploring Social Media Post-authors’ Perspectives ACL 2023 On the Risk of Misinformation Pollution with Large Language Models EMNLP 2023 On the Trade-Off between Actionable Explanations and the Right to be Forgotten ICLR 2023 On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks NeurIPS 2023 PEFTDebias : Capturing debiasing information using PEFTs EMNLP 2023 Performance and Risk Trade-offs for Multi-word Text Prediction at Scale EACL 2023 ‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion EMNLP 2023 PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation CVPR 2023 Pretraining Language Models with Human Preferences ICML 2023 Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? NeurIPS 2023 Privacy-Preserving End-to-End Spoken Language Understanding IJCAI 2023 Privacy Risks in Speech Emotion Recognition: A Systematic Study on Gender Inference Attack Interspeech 2023 Private Everlasting Prediction NeurIPS 2023 Prompting GPT-3 To Be Reliable ICLR 2023 ProPILE: Probing Privacy Leakage in Large Language Models NeurIPS 2023 Protecting Language Generation Models via Invisible Watermarking ICML 2023 Proximity-Informed Calibration for Deep Neural Networks NeurIPS 2023 Purifier: Defending Data Inference Attacks via Transforming Confidence Scores AAAI 2023