20 citations · 70 across the 17 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
The Solvability of Interpretability Evaluation Metrics
Yilun Zhou, Julie Shah
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency. In this paper,…
cs.CL2022★ 1 cited
ExSum: From Local Explanations to Model Understanding
Yilun Zhou, Marco Tulio Ribeiro, Julie Shah
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires bot…