4 papers · 1 filter
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Julian Skirzynski, Harry Cheon, Shreyas Kadekodi +2
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few data…
Bridging Prediction and Intervention Problems in Social Systems
Lydia T. Liu, Inioluwa Deborah Raji, Angela Zhou +32
Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals…
Observational Multiplicity
Erin George, Deanna Needell, Berk Ustun
Many prediction tasks can admit multiple models that can perform almost equally well. This phenomenon can can undermine interpretability and safety when competing models assign con…
Classification with Conceptual Safeguards
Hailey Joren, Charles Marx, Berk Ustun
We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for mod…