Three Levels of AI Transparency

Kashyap Haresamudram; Stefan Larsson; Fredrik Heintz

doi:10.1109/MC.2022.3213181

Three Levels of AI Transparency

Kashyap Haresamudram, Stefan Larsson, Fredrik Heintz

Department of Technology and Society

Linköping University

Research output: Contribution to journal › Article › peer-review

17 Downloads (Pure)

Abstract

Transparency is generally cited as a key consideration towards building Trustworthy AI. However, the concept of transparency is fragmented in AI research, often limited to transparency of the algorithm alone. While considerable attempts have been made to expand the scope beyond the algorithm, there has yet to be a holistic approach that includes not only the AI system, but also the user, and society at large. We propose that AI transparency operates on three levels, (1) Algorithmic Transparency, (2) Interaction Transparency, and (3) Social Transparency, all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.

Original language	English
Journal	Computer
DOIs	https://doi.org/10.1109/MC.2022.3213181
Publication status	Accepted/In press - 2022 Oct 4

Bibliographical note

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Subject classification (UKÄ)

Interaction Technologies
Social Sciences Interdisciplinary
Information Systems, Social aspects

Keywords

Artificial Intelligence
Transparency
Algorithm
Interaction
Society
Governance

Access to Document

10.1109/MC.2022.3213181

Three Levels of AI TransparencyAccepted author manuscript, 562 KB

1 Active

AI Transparency and Consumer Trust
Larsson, S., Heintz, F., Söderlund, K., Haresamudram, K., Tanqueray, L. & White, J.
2020/01/01 → 2024/12/31
Project: Research

1 Invited talk

AI Governance - Social Norms and interdisciplinary needs
Stefan Larsson (Presenter)
2022 Nov 16
Activity: Talk or presentation › Invited talk

Cite this

@article{9405ca170949443e8cad977f38c2df4f,

title = "Three Levels of AI Transparency",

abstract = "Transparency is generally cited as a key consideration towards building Trustworthy AI. However, the concept of transparency is fragmented in AI research, often limited to transparency of the algorithm alone. While considerable attempts have been made to expand the scope beyond the algorithm, there has yet to be a holistic approach that includes not only the AI system, but also the user, and society at large. We propose that AI transparency operates on three levels, (1) Algorithmic Transparency, (2) Interaction Transparency, and (3) Social Transparency, all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.",

keywords = "Artificial Intelligence, Transparency, Algorithm, Interaction, Society, Governance",

author = "Kashyap Haresamudram and Stefan Larsson and Fredrik Heintz",

note = "{\textcopyright} 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",

year = "2022",

month = oct,

day = "4",

doi = "10.1109/MC.2022.3213181",

language = "English",

journal = "Computer",

issn = "1558-0814",

publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Three Levels of AI Transparency

AU - Haresamudram, Kashyap

AU - Larsson, Stefan

AU - Heintz, Fredrik

N1 - © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2022/10/4

Y1 - 2022/10/4

N2 - Transparency is generally cited as a key consideration towards building Trustworthy AI. However, the concept of transparency is fragmented in AI research, often limited to transparency of the algorithm alone. While considerable attempts have been made to expand the scope beyond the algorithm, there has yet to be a holistic approach that includes not only the AI system, but also the user, and society at large. We propose that AI transparency operates on three levels, (1) Algorithmic Transparency, (2) Interaction Transparency, and (3) Social Transparency, all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.

AB - Transparency is generally cited as a key consideration towards building Trustworthy AI. However, the concept of transparency is fragmented in AI research, often limited to transparency of the algorithm alone. While considerable attempts have been made to expand the scope beyond the algorithm, there has yet to be a holistic approach that includes not only the AI system, but also the user, and society at large. We propose that AI transparency operates on three levels, (1) Algorithmic Transparency, (2) Interaction Transparency, and (3) Social Transparency, all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.

KW - Artificial Intelligence

KW - Transparency

KW - Algorithm

KW - Interaction

KW - Society

KW - Governance

U2 - 10.1109/MC.2022.3213181

DO - 10.1109/MC.2022.3213181

M3 - Article

JO - Computer

JF - Computer

SN - 1558-0814

ER -

Three Levels of AI Transparency

Abstract

Bibliographical note

Subject classification (UKÄ)

Keywords

Access to Document

Fingerprint

Projects

AI Transparency and Consumer Trust

Activities

AI Governance - Social Norms and interdisciplinary needs

Cite this