Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study

Sz-Ting Tzeng; Nirav Ajmeri; Munindar P. Singh

doi:10.3233/FAIA240917

Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study

Sz-Ting Tzeng, Nirav Ajmeri, Munindar P. Singh

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

We propose Exanna, a framework to realize agents that incorporate values in decision making.
An Exanna agent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others.
Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.

Original language	English
Title of host publication	ECAI
Subtitle of host publication	Proceedings of the 27th European Conference on Artificial Intelligence (ECAI)
Editors	Ulle Endriss, Francisco S. Melo, Kerstin Bach, Alberto Bugarín-Diz, José M. Alonso-Moral, Senén Barro, Fredrik Heintz
Place of Publication	Santiago de Compostela, Spain
Publisher	IOS Press
Pages	3612-3619
Number of pages	8
ISBN (Electronic)	9781643685489
DOIs	https://doi.org/10.3233/FAIA240917
Publication status	Published - 24 Oct 2024
Event	27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE - Galicia, Santiago de Compostela, Spain Duration: 19 Oct 2024 → 24 Oct 2024 https://www.ecai2024.eu/calls/main-track

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Publisher	IOS Press
Volume	392
ISSN (Print)	0922-6389
ISSN (Electronic)	1879-8314

Conference

Conference	27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE
Abbreviated title	ecai2024.
Country/Territory	Spain
City	Santiago de Compostela
Period	19/10/24 → 24/10/24
Internet address	https://www.ecai2024.eu/calls/main-track

Bibliographical note

Publisher Copyright:
© 2024 The Authors.

Research Groups and Themes

Intelligent Systems Laboratory

Access to Document

10.3233/FAIA240917Licence: CC BY-NC

https://export.arxiv.org/abs/2408.02117Licence: CC BY

Handle.net

Persistent link

Cite this

Tzeng, S.-T., Ajmeri, N., & Singh, M. P. (2024). Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study. In U. Endriss, F. S. Melo, K. Bach, A. Bugarín-Diz, J. M. Alonso-Moral, S. Barro, & F. Heintz (Eds.), ECAI: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI) (pp. 3612-3619). (Frontiers in Artificial Intelligence and Applications; Vol. 392). IOS Press. https://doi.org/10.3233/FAIA240917

Tzeng, Sz-Ting ; Ajmeri, Nirav ; Singh, Munindar P. / Value-Based Rationales Improve Social Experience : A Multiagent Simulation Study. ECAI: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI). editor / Ulle Endriss ; Francisco S. Melo ; Kerstin Bach ; Alberto Bugarín-Diz ; José M. Alonso-Moral ; Senén Barro ; Fredrik Heintz. Santiago de Compostela, Spain : IOS Press, 2024. pp. 3612-3619 (Frontiers in Artificial Intelligence and Applications).

@inproceedings{3d5592e89bd8434c93b27a9e489f922f,

title = "Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study",

abstract = "We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exanna agent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility. ",

author = "Sz-Ting Tzeng and Nirav Ajmeri and Singh, {Munindar P.}",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors.; 27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, ecai2024. ; Conference date: 19-10-2024 Through 24-10-2024",

year = "2024",

month = oct,

day = "24",

doi = "10.3233/FAIA240917",

language = "English",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press",

pages = "3612--3619",

editor = "Ulle Endriss and Melo, {Francisco S.} and Kerstin Bach and Alberto Bugar{\'i}n-Diz and Alonso-Moral, {Jos{\'e} M.} and Sen{\'e}n Barro and Fredrik Heintz",

booktitle = "ECAI",

address = "Netherlands",

url = "https://www.ecai2024.eu/calls/main-track",

}

Tzeng, S-T, Ajmeri, N & Singh, MP 2024, Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study. in U Endriss, FS Melo, K Bach, A Bugarín-Diz, JM Alonso-Moral, S Barro & F Heintz (eds), ECAI: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI). Frontiers in Artificial Intelligence and Applications, vol. 392, IOS Press, Santiago de Compostela, Spain, pp. 3612-3619, 27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, Santiago de Compostela, Spain, 19/10/24. https://doi.org/10.3233/FAIA240917

Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study. / Tzeng, Sz-Ting; Ajmeri, Nirav; Singh, Munindar P.
ECAI: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI). ed. / Ulle Endriss; Francisco S. Melo; Kerstin Bach; Alberto Bugarín-Diz; José M. Alonso-Moral; Senén Barro; Fredrik Heintz. Santiago de Compostela, Spain: IOS Press, 2024. p. 3612-3619 (Frontiers in Artificial Intelligence and Applications; Vol. 392).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Value-Based Rationales Improve Social Experience

T2 - 27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE

AU - Tzeng, Sz-Ting

AU - Ajmeri, Nirav

AU - Singh, Munindar P.

PY - 2024/10/24

Y1 - 2024/10/24

N2 - We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exanna agent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.

AB - We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exanna agent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.

U2 - 10.3233/FAIA240917

DO - 10.3233/FAIA240917

M3 - Conference Contribution (Conference Proceeding)

T3 - Frontiers in Artificial Intelligence and Applications

SP - 3612

EP - 3619

BT - ECAI

A2 - Endriss, Ulle

A2 - Melo, Francisco S.

A2 - Bach, Kerstin

A2 - Bugarín-Diz, Alberto

A2 - Alonso-Moral, José M.

A2 - Barro, Senén

A2 - Heintz, Fredrik

PB - IOS Press

CY - Santiago de Compostela, Spain

Y2 - 19 October 2024 through 24 October 2024

ER -

Tzeng ST, Ajmeri N, Singh MP. Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study. In Endriss U, Melo FS, Bach K, Bugarín-Diz A, Alonso-Moral JM, Barro S, Heintz F, editors, ECAI: Proceedings of the 27th European Conference on Artificial Intelligence (ECAI). Santiago de Compostela, Spain: IOS Press. 2024. p. 3612-3619. (Frontiers in Artificial Intelligence and Applications). doi: 10.3233/FAIA240917

Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study

Abstract

Publication series

Conference

Bibliographical note

Research Groups and Themes

Access to Document

Handle.net

Fingerprint

Cite this