Why, who, what, when and how about explainability in human-agent systems

Avi Rosenfeld; Ariella Richardson

Why, who, what, when and how about explainability in human-agent systems

Avi Rosenfeld, Ariella Richardson

Jerusalem College of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

This paper presents a survey of issues relating to explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it needs to evaluate all other issues regarding explainability.

Original language	English
Title of host publication	Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
Editors	Bo An, Amal El Fallah Seghrouchni, Gita Sukthankar
Publisher	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages	2161-2164
Number of pages	4
ISBN (Electronic)	9781450375184
State	Published - 2020
Externally published	Yes
Event	19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 - Virtual, Auckland, New Zealand Duration: 19 May 2020 → …

Publication series

Name	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume	2020-May
ISSN (Print)	1548-8403
ISSN (Electronic)	1558-2914

Conference

Conference	19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
Country/Territory	New Zealand
City	Virtual, Auckland
Period	19/05/20 → …

Bibliographical note

Publisher Copyright:
© 2020 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). All rights reserved.

Keywords

Human-agent systems
Machine learning interpretability
Machine learning transparency
XAI

Cite this

Rosenfeld, A., & Richardson, A. (2020). Why, who, what, when and how about explainability in human-agent systems. In B. An, A. El Fallah Seghrouchni, & G. Sukthankar (Eds.), Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 (pp. 2161-2164). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 2020-May). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Rosenfeld, Avi ; Richardson, Ariella. / Why, who, what, when and how about explainability in human-agent systems. Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. editor / Bo An ; Amal El Fallah Seghrouchni ; Gita Sukthankar. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2020. pp. 2161-2164 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

@inproceedings{875f4119d2cd4ecc91c33fe2197b037e,

title = "Why, who, what, when and how about explainability in human-agent systems",

abstract = "This paper presents a survey of issues relating to explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it needs to evaluate all other issues regarding explainability.",

keywords = "Human-agent systems, Machine learning interpretability, Machine learning transparency, XAI",

author = "Avi Rosenfeld and Ariella Richardson",

note = "Publisher Copyright: {\textcopyright} 2020 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). All rights reserved.; 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 ; Conference date: 19-05-2020",

year = "2020",

language = "אנגלית",

series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

pages = "2161--2164",

editor = "Bo An and {El Fallah Seghrouchni}, Amal and Gita Sukthankar",

booktitle = "Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020",

}

Rosenfeld, A & Richardson, A 2020, Why, who, what, when and how about explainability in human-agent systems. in B An, A El Fallah Seghrouchni & G Sukthankar (eds), Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, vol. 2020-May, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2161-2164, 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020, Virtual, Auckland, New Zealand, 19/05/20.

Why, who, what, when and how about explainability in human-agent systems. / Rosenfeld, Avi; Richardson, Ariella.
Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. ed. / Bo An; Amal El Fallah Seghrouchni; Gita Sukthankar. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2020. p. 2161-2164 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 2020-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Why, who, what, when and how about explainability in human-agent systems

AU - Rosenfeld, Avi

AU - Richardson, Ariella

PY - 2020

Y1 - 2020

N2 - This paper presents a survey of issues relating to explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it needs to evaluate all other issues regarding explainability.

AB - This paper presents a survey of issues relating to explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it needs to evaluate all other issues regarding explainability.

KW - Human-agent systems

KW - Machine learning interpretability

KW - Machine learning transparency

KW - XAI

UR - http://www.scopus.com/inward/record.url?scp=85096667722&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85096667722

T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

SP - 2161

EP - 2164

BT - Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020

A2 - An, Bo

A2 - El Fallah Seghrouchni, Amal

A2 - Sukthankar, Gita

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

T2 - 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020

Y2 - 19 May 2020

ER -

Rosenfeld A, Richardson A. Why, who, what, when and how about explainability in human-agent systems. In An B, El Fallah Seghrouchni A, Sukthankar G, editors, Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2020. p. 2161-2164. (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

Why, who, what, when and how about explainability in human-agent systems

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this