loading page

DARPA’s Explainable AI (XAI) program: A retrospective
  • +1
  • David Gunning,
  • Eric Vorm,
  • Yunyan Wang,
  • Matt Turek
David Gunning
DARPA

Corresponding Author:david.r.gunning@gmail.com

Author Profile
Eric Vorm
US Naval Research Laboratory
Author Profile
Yunyan Wang
Quantitative Scientific Solutions
Author Profile
Matt Turek
DARPA
Author Profile

Abstract

DARPA formulated the Explainable Artificial Intelligence (XAI) program in 2015 with the goal to enable end users to better understand, trust, and effectively manage artificially intelligent systems. In 2017, the four-year XAI research program began. Now, as XAI comes to an end in 2021, it is time to reflect on what succeeded, what failed, and what was learned. This article summarizes the goals, organization, and research progress of the XAI Program.
09 Nov 2021Submitted to Applied AI Letters
11 Nov 2021Submission Checks Completed
11 Nov 2021Assigned to Editor
15 Nov 2021Review(s) Completed, Editorial Evaluation Pending
15 Nov 2021Editorial Decision: Revise Minor
29 Nov 20211st Revision Received
30 Nov 2021Submission Checks Completed
30 Nov 2021Assigned to Editor
30 Nov 2021Review(s) Completed, Editorial Evaluation Pending
30 Nov 2021Editorial Decision: Accept