-
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Influence functions approximate the 'influences' of training data-points...
read it
-
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?
Data collection for natural language (NL) understanding tasks has increa...
read it
-
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?
Algorithmic approaches to interpreting machine learning models have prol...
read it
-
Interpretable Image Recognition with Hierarchical Prototypes
Vision models are interpretable when they classify objects on the basis ...
read it
-
Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation
We provide code that produces beautiful poetry. Our sonnet-generation al...
read it

Peter Hase
