The notions of trust and trustworthiness in the field of AI are currently the focus of a collective, interdisciplinary effort for clarification. In this work, we contribute to this ongoing debate by identifying two senses in which an agent might place trust in an AI system. The first sense, referring to trustworthiness as formalised in previous work, considers the results of tests conducted on the system alongside the agent’s expectations. The second sense, extends the former by factoring in the agent’s “pragmatic” background when considering these tests. We argue that these two forms of trust can be understood in relation to well-known approaches in statistical inference: the first aligns with a frequentist interpretation, while the second reflects a Bayesian view of trust.
Prior to Trust: Frequentist and Bayesian views of Trust in AI / M. Petrolo, E. Kubyshkina, G. Primiero (CEUR WORKSHOP PROCEEDINGS). - In: BEWARE 2024 : Bias, Risk, Explainability, Ethical AI and the role of Logic and Logic Programming 2024 / [a cura di] G. Coraglia, F. A. D’Asaro, A. Dyoub, F. A. Lissi, G. Primiero. - Prima edizione. - [s.l] : CEUR-Ws, 2024 Dec. - pp. 1-5 (( convegno 3rd Workshop on Bias, Ethical AI, Explainability and the role of Logic and Logic Programming co-located with the 23rd International Conference of the Italian Association for Artificial Intelligence tenutosi a Bolzano nel 2024.
Prior to Trust: Frequentist and Bayesian views of Trust in AI
E. KubyshkinaSecondo
;G. PrimieroUltimo
2024
Abstract
The notions of trust and trustworthiness in the field of AI are currently the focus of a collective, interdisciplinary effort for clarification. In this work, we contribute to this ongoing debate by identifying two senses in which an agent might place trust in an AI system. The first sense, referring to trustworthiness as formalised in previous work, considers the results of tests conducted on the system alongside the agent’s expectations. The second sense, extends the former by factoring in the agent’s “pragmatic” background when considering these tests. We argue that these two forms of trust can be understood in relation to well-known approaches in statistical inference: the first aligns with a frequentist interpretation, while the second reflects a Bayesian view of trust.File | Dimensione | Formato | |
---|---|---|---|
Prior to Trust.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
175.53 kB
Formato
Adobe PDF
|
175.53 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.