Modelling Trust in Human-AI Interaction: Doctoral Consortium

S. Mehrotra

Abstract

Trust is an important element of any interaction, but especially when we are interacting with a piece of technology which does not think like we do. Therefore, AI systems need to understand how humans trust them, and what to do to promote appropriate trust. The aim of this research is to study trust through both a formal and social lens. We will be working on formal models of trust, but with a focus on the social nature of trust in order to represent how humans trust AI. We will then employ methods from human computer interaction research to study if these models work in practice, and what would eventually be necessary for systems to elicit appropriate levels of trust from their users. The context of this research will be AI agents which interact with their users to offer personal support.

Original language	English
Pages	1826-1828
Publication status	Published - 3 May 2021
Event	20th International Conference on Autonomous Agentsand Multiagent Systems - Virtual/online event due to COVID-19 Duration: 3 May 2021 → 7 May 2021 Conference number: 20

Conference

Conference	20th International Conference on Autonomous Agentsand Multiagent Systems
Abbreviated title	AAMAS 2021
Period	3/05/21 → 7/05/21

Bibliographical note

The author thanks Myrthe L. Tielman and Catholijn M. Jonker for their supervision and support.

Keywords

Trust
AI agents
Values
Value Similarity
Social Situations

Access to Document

p1826Final published version, 810 KB

https://dl.acm.org/doi/abs/10.5555/3463952.3464253

2 Conference contribution
1 Poster
1 Article

Integrity-based Explanations for Fostering Appropriate Trust in AI Agents
Mehrotra, S., Centeio Jorge, C., Jonker, C. M. & Tielman, M. L., 2024, In: ACM Transactions on Interactive Intelligent Systems. 14, 1, 36 p., 4.
Research output: Contribution to journal › Article › Scientific › peer-review

Open Access
File
2 Citations (Scopus)

45 Downloads (Pure)
Building Appropriate Trust in AI: The Significance of Integrity-Centered Explanations
Mehrotra, S., Centeio Jorge, C., Jonker, C. M. & Tielman, M. L., 2023, p. 436-439. 4 p.
Research output: Contribution to conference › Poster › Scientific

Open Access
File
68 Downloads (Pure)
More Similar Values, More Trust? - the Effect of Value Similarity on Trust in Human-Agent Interaction
Mehrotra, S., Jonker, C. M. & Tielman, M. L., 21 Jul 2021, AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society. ACM DL, p. 777-783 7 p.
Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Open Access
File
6 Citations (Scopus)

74 Downloads (Pure)

Cite this

@conference{6a01c505f21e43c5b472bc93ee5a1a16,

title = "Modelling Trust in Human-AI Interaction: Doctoral Consortium",

abstract = "Trust is an important element of any interaction, but especially when we are interacting with a piece of technology which does not think like we do. Therefore, AI systems need to understand how humans trust them, and what to do to promote appropriate trust. The aim of this research is to study trust through both a formal and social lens. We will be working on formal models of trust, but with a focus on the social nature of trust in order to represent how humans trust AI. We will then employ methods from human computer interaction research to study if these models work in practice, and what would eventually be necessary for systems to elicit appropriate levels of trust from their users. The context of this research will be AI agents which interact with their users to offer personal support.",

keywords = "Trust, AI agents, Values, Value Similarity, Social Situations",

author = "S. Mehrotra",

note = "The author thanks Myrthe L. Tielman and Catholijn M. Jonker for their supervision and support.; 20th International Conference on Autonomous Agentsand Multiagent Systems, AAMAS 2021 ; Conference date: 03-05-2021 Through 07-05-2021",

year = "2021",

month = may,

day = "3",

language = "English",

pages = "1826--1828",

}

TY - CONF

T1 - Modelling Trust in Human-AI Interaction

T2 - 20th International Conference on Autonomous Agentsand Multiagent Systems

AU - Mehrotra, S.

N1 - Conference code: 20

PY - 2021/5/3

Y1 - 2021/5/3

N2 - Trust is an important element of any interaction, but especially when we are interacting with a piece of technology which does not think like we do. Therefore, AI systems need to understand how humans trust them, and what to do to promote appropriate trust. The aim of this research is to study trust through both a formal and social lens. We will be working on formal models of trust, but with a focus on the social nature of trust in order to represent how humans trust AI. We will then employ methods from human computer interaction research to study if these models work in practice, and what would eventually be necessary for systems to elicit appropriate levels of trust from their users. The context of this research will be AI agents which interact with their users to offer personal support.

AB - Trust is an important element of any interaction, but especially when we are interacting with a piece of technology which does not think like we do. Therefore, AI systems need to understand how humans trust them, and what to do to promote appropriate trust. The aim of this research is to study trust through both a formal and social lens. We will be working on formal models of trust, but with a focus on the social nature of trust in order to represent how humans trust AI. We will then employ methods from human computer interaction research to study if these models work in practice, and what would eventually be necessary for systems to elicit appropriate levels of trust from their users. The context of this research will be AI agents which interact with their users to offer personal support.

KW - Trust

KW - AI agents

KW - Values

KW - Value Similarity

KW - Social Situations

M3 - Abstract

SP - 1826

EP - 1828

Y2 - 3 May 2021 through 7 May 2021

ER -

Modelling Trust in Human-AI Interaction: Doctoral Consortium

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

Integrity-based Explanations for Fostering Appropriate Trust in AI Agents

Building Appropriate Trust in AI: The Significance of Integrity-Centered Explanations

More Similar Values, More Trust? - the Effect of Value Similarity on Trust in Human-Agent Interaction

Cite this