Safe and Trustworthy AI Workshop 2022
Some of the authors agreed to have their posters published online. See below ordered by title.
- Argument-Based Dialogues for Joint Human and Machine Moral Reasoning
- Argumentation for Bias Detection, Explanation, and Mitigation in Decision-Making Systems
- Assurance of Machine Learning for use in Autonomous Systems
- Bootstrapping Models to Critique Chain-of-Thought Rationales for n-Digit Arithmetic Problems
- Clinically Validating Explanations for Fetal Brain Ultrasound
- Creating a Conceptual Framework for the Design and Deployment of Autonomous Systems from an Intersectional Perspective
- Debating Ethics: Using Natural Language Datasets to Support Human and AI Debate
- Deep Learning with Requirements
- Edge-Level Privacy in Graph Neural Networks
- Explainable AI for High Resolution Images
- Failure Detection in Medical Image Classification: a Reality Check and Benchmarking Testbed
- Is AI an Existential Risk
- Not so Fair: Machine Learning and its Impacts
- Reasoning about Causality in Games
- Saliency Mapping with Hierarchical Perturbation
- Sociotechnical Requirements Engineering for Data Science Systems
- Sufficient Conditions for Cooperation Between Rational Agents
- Towards Ecological Machine Ethics
- Towards Scalable Evaluation of Cooperativeness in Language Models
- Trustworthy Adaptation of DNN Classifiers
- Visual Debates