PhilSci Archive

Verifiability as a Complement to AI Explainability: A Conceptual Proposal

Patil, Kaustubh R. and Heinrichs, Bert (2022) Verifiability as a Complement to AI Explainability: A Conceptual Proposal. [Preprint]

[img]
Preview
Text
Verification as a Complement to AI Explainability#final.pdf

Download (387kB) | Preview

Abstract

Recent advances in the field of artificial intelligence (AI) are providing automated and in many cases improved decision-making. However, even very reliable AI systems can go terribly wrong without human users understanding the reason for it. Against this background, there are now widespread calls for models of “explainable AI”. In this paper we point out some inherent problems of this concept and argue that explainability alone is probably not the solution. We therefore propose another approach as a complement, which we call “verifiability”. In essence, it is about designing AI so that it makes available multiple verifiable predictions (given a ground truth) in addition to the one desired prediction that cannot be verified because the ground truth is missing. Such verifiable AI could help to further minimize serious mistakes despite a lack of explainability, help increase their trustworthiness and in turn improve societal acceptance of AI.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Patil, Kaustubh R.0000-0002-0289-5480
Heinrichs, Bert0000-0002-0181-0078
Keywords: Artificial intelligence (AI), machine learning, explainability, verifiability, reliability
Subjects: Specific Sciences > Artificial Intelligence
Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User: Dr. Bert Heinrichs
Date Deposited: 11 Mar 2022 02:13
Last Modified: 11 Mar 2022 02:13
Item ID: 20297
Subjects: Specific Sciences > Artificial Intelligence
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 4 March 2022
URI: https://philsci-archive.pitt.edu/id/eprint/20297

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item