English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Trust is a central component of the interaction between people and AI, inthat 'incorrect' levels of trust may cause misuse, abuse or disuse of thetechnology. But what, precisely, is the nature of trust in AI? What are theprerequisites and goals of the cognitive mechanism of trust, and how can wepromote them, or assess whether they are being satisfied in a giveninteraction? This work aims to answer these questions. We discuss a model oftrust inspired by, but not identical to, sociology's interpersonal trust (i.e.,trust between people). This model rests on two key properties of thevulnerability of the user and the ability to anticipate the impact of the AImodel's decisions. We incorporate a formalization of 'contractual trust', suchthat trust between a user and an AI is trust that some implicit or explicitcontract will hold, and a formalization of 'trustworthiness' (which detachesfrom the notion of trustworthiness in sociology), and with it concepts of'warranted' and 'unwarranted' trust. We then present the possible causes ofwarranted trust as intrinsic reasoning and extrinsic behavior, and discuss howto design trustworthy AI, how to evaluate whether trust has manifested, andwhether it is warranted. Finally, we elucidate the connection between trust andXAI using our formalization.

Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI