Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance
If a user is presented an AI system that portends to explain how it works, how do we know
whether the explanation works and the user has achieved a pragmatic understanding of the …
whether the explanation works and the user has achieved a pragmatic understanding of the …
Visual analytics for machine learning: A data perspective survey
The past decade has witnessed a plethora of works that leverage the power of visualization
(VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML …
(VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML …
How does AAR/AI Support Problem Solvers with Diverse Behaviors and Cognitive Styles?
R Dikkala - 2022 - ir.library.oregonstate.edu
Abstract" What's wrong with this AI?" Explainable AI (XAI) researchers are moving beyond
explaining an AI's actions, to helping users detect an AI's failures. However this detection …
explaining an AI's actions, to helping users detect an AI's failures. However this detection …
Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL
KH Lam, D Tabatabai, J Irvine, D Bertucci… - Proceedings of the …, 2022 - ojs.aaai.org
Reinforcement learning (RL) agents are commonly evaluated via their expected value over
a distribution of test scenarios. Unfortunately, this evaluation approach provides limited …
a distribution of test scenarios. Unfortunately, this evaluation approach provides limited …