Human Uncertainty in Concept-Based AI Systems
Collins, Katherine M., Barker, Matthew, Zarlenga, Mateo Espinosa, Raman, Naveen, Bhatt, Umang, Jamnik, Mateja, Sucholutsky, Ilia, Weller, Adrian, Dvijotham, Krishnamurthy
–arXiv.org Artificial Intelligence
Placing a human in the loop may abate the risks of deploying AI systems in safety-critical settings (e.g., a clinician working with a medical AI system). However, mitigating risks arising from human error and uncertainty within such human-AI interactions is an important and understudied issue. In this work, we study human uncertainty in the context of concept-based models, a family of AI systems that enable human feedback via concept interventions where an expert intervenes on human-interpretable concepts relevant to the task. Prior work in this space often assumes that humans are oracles who are always certain and correct. Yet, real-world decision-making by humans is prone to occasional mistakes and uncertainty. We study how existing concept-based models deal with uncertain interventions from humans using two novel datasets: UMNIST, a visual dataset with controlled simulated uncertainty based on the MNIST dataset, and CUB-S, a relabeling of the popular CUB concept dataset with rich, densely-annotated soft labels from humans. We show that training with uncertain concept labels may help mitigate weaknesses of concept-based systems when handling uncertain interventions. These results allow us to identify several open challenges, which we argue can be tackled through future multidisciplinary research on building interactive uncertainty-aware systems. To facilitate further research, we release a new elicitation platform, UElic, to collect uncertain feedback from humans in collaborative prediction tasks.
arXiv.org Artificial Intelligence
Mar-22-2023
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.28)
- North America > United States (0.46)
- Europe > United Kingdom
- Genre:
- Research Report (1.00)
- Industry:
- Health & Medicine > Diagnostic Medicine > Imaging (0.46)
- Technology: