Dr. Siddharth Mehrotra

Postdoc Researcher

Trust should correspond to Trustworthiness: a Formalization of Appropriate Mutual Trust in Human-Agent Teams


Conference


Carolina Centeio Jorge, Siddharth Mehrotra, Catholijn M. Jonker, Myrthe L. Tielman
AAMAS Proceedings of the 22nd International Workshop on Trust in Agent Societies, London, UK, D. Wang R. Falcone J. Zhang, vol. 3022, CEUR-WS.org, 2021

DOI: urn:nbn:de:0074-3022-0

PDF
Cite

Cite

APA   Click to copy
Jorge, C. C., Mehrotra, S., Jonker, C. M., & Tielman, M. L. (2021). Trust should correspond to Trustworthiness: a Formalization of Appropriate Mutual Trust in Human-Agent Teams. In D. W. R. Falcone J. Zhang (Ed.) (Vol. 3022). CEUR-WS.org. https://doi.org/urn:nbn:de:0074-3022-0


Chicago/Turabian   Click to copy
Jorge, Carolina Centeio, Siddharth Mehrotra, Catholijn M. Jonker, and Myrthe L. Tielman. “Trust Should Correspond to Trustworthiness: a Formalization of Appropriate Mutual Trust in Human-Agent Teams.” In , edited by D. Wang R. Falcone J. Zhang. Vol. 3022. AAMAS Proceedings of the 22nd International Workshop on Trust in Agent Societies, London, UK. CEUR-WS.org, 2021.


MLA   Click to copy
Jorge, Carolina Centeio, et al. Trust Should Correspond to Trustworthiness: a Formalization of Appropriate Mutual Trust in Human-Agent Teams. Edited by D. Wang R. Falcone J. Zhang, vol. 3022, CEUR-WS.org, 2021, doi:urn:nbn:de:0074-3022-0.


BibTeX   Click to copy

@conference{carolina2021a,
  title = {Trust should correspond to Trustworthiness: a Formalization of Appropriate Mutual Trust in Human-Agent Teams},
  year = {2021},
  month = dec,
  publisher = {CEUR-WS.org},
  series = {AAMAS Proceedings of the 22nd International Workshop on Trust in Agent Societies, London, UK},
  volume = {3022},
  doi = {urn:nbn:de:0074-3022-0},
  author = {Jorge, Carolina Centeio and Mehrotra, Siddharth and Jonker, Catholijn M. and Tielman, Myrthe L.},
  editor = {R. Falcone, J. Zhang, D. Wang},
  month_numeric = {12}
}

Abstract:
In human-agent teams, how one teammate trusts another teammate should correspond to the latter’s actual trustworthiness, creating what we would call appropriate mutual trust. Although this sounds obvious, the notion of appropriate mutual trust for human-agent teamwork lacks a formal definition. In this article, we propose a formalization which represents trust as a belief about trustworthiness. Then, we address mutual trust, and pose that agents can use beliefs about trustworthiness to represent how they trust their human teammates, as well as to reason about how their human teammates trust them. This gives us a formalization with nested beliefs about beliefs of trustworthiness. Next, we highlight that mutual trust should also be appropriate, where we define appropriate trust in an agent as the trust which corresponds directly to that agent’s trustworthiness. Finally, we explore how agents can define their own trustworthiness, using the concepts of ability, benevolence and integrity. This formalization of appropriate mutual trust can form the base for developing agents which can promote such trust. 

Share

Tools
Translate to