Research: Explainable AI

Contents

I am working on the DARPA XAI Program with Robert Hoffman and Gary Klein, along with several of my students. We are supporting Technical Area 2–development of a naturalistic and computational psychological model of explanation in AI systems.

Follow our Explainable AI Project at Researchgate

Relevant Publications

2019

Mueller, Shane T; Tan, Yin-Yin (Sarah)

How Many Personality Configurations Exist? Clustering analysis produces a different answer than does factor analysis. Online

Klein, Gary (Ed.): Psychology Today | Seeing what others don't 2019.

Abstract | Links | BibTeX

Roberto Confalonieri Tarek Besold, Tillman Weyde Kathleen Creel Tania Lombrozo Shane Mueller ; Shafto, Patrick

What makes a good explanation? Cognitive dimensions of explaining intelligent machines Conference

Symposium presented at the 41st Annual Conference of the Cognitive Science Society, Cognitive Science Society Cognitive Science Society, Montreal, QB, CA, 2019.

Links | BibTeX

Klein, Gary; Hoffman, Robert; Mueller, Shane T

Naturalistic psychological model of explanatory reasoning: How people explain things to others and themselves Inproceedings

Proceedings of the International Conference on Naturalistic Decision Making, 2019.

Links | BibTeX

Klein, Gary; Hoffman, Robert; Mueller, Shane

Mindless Self-Explaining vs Meaningful Self-Explaining Conference

International Conference on Naturalistic Decision Making, San Francisco, CA, 2019.

BibTeX

Shane Mueller Gary Klein, Robert Hoffman Jeffrey Morrison James Tittle & Peter Pirolli

AI Symposium: Current Issues and Challenges in Artificial Intelligence Conference

The 14th International Conference on Naturalistic Decision Making, San Francisco, CA, 2019.

BibTeX

Linja, Anne; Alam, Lamia; Mueller, Shane T

What the AI Saw: Examining human predictions of deep image classification errors Conference

Midwest Cognitive Science, Columbus, OH, 2019.

Abstract | Links | BibTeX

2018

Mueller, Shane T; Nelson, Brittany

A Computational Model of Sensemaking in a Hurricane Prediction Task Inproceedings

Proceedings of the International Conference on Cognitive Modeling, 2018.

Links | BibTeX

Hoffman, Robert; Miller, Tim; Mueller, Shane T; Klein, Gary; Clancey, William J

Explaining Explanation, Part 4: A Deep Dive on Deep Nets Journal Article

IEEE Intelligent Systems, 33 (3), pp. 87–95, 2018.

Links | BibTeX

Hoffman, Robert R; Klein, Gary; Mueller, Shane T

Explaining Explanation For “Explainable AI” Inproceedings

Proceedings of the Human Factors and Ergonomics Society Annual Meeting, pp. 197–201, SAGE Publications 2018.

Links | BibTeX

Hoffman, Robert R; Mueller, Shane T; Klein, Gary; Litman, Jordan

Metrics for Explainable AI: Challenges and Prospects Journal Article

arXiv preprint arXiv:1812.04608, 2018.

Links | BibTeX

Mueller, Shane T; Hoffman, Robert R; Clancey, William J; Emrey, Abigail; Klein, Gary

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI. Technical Report

Institute for Human and Machine Cognition 2018.

Links | BibTeX

2017

Hoffman, Robert R; Mueller, Shane T; Klein, Gary

Explaining Explanation, Part 2: Empirical Foundations Journal Article

IEEE Intelligent Systems, 32 (4), pp. 78–86, 2017.

Links | BibTeX

2011

Mueller, Shane T; Klein, Gary

Improving users' mental models of intelligent software tools Journal Article

IEEE Intelligent Systems, 26 (2), pp. 77–83, 2011.

BibTeX

2009

Mueller, Shane T; Klein, Gary; Burns, Christopher

Experiencing the tool without experiencing the pain: concepts for an experiential user guide Inproceedings

Proc. 9th Int’l Conf. Naturalistic Decision Making, pp. 105–112, 2009.

BibTeX