conftrace_

model simulatability

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

leakage-adjusted evaluation (1) algorithmic explanation (1) natural language explanation (1) explanation faithfulness (1) human evaluation (1) feature importance (1) explainable ai (1) explanation generation (1)

Papers

Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? ACL 2020 Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? EMNLP 2020