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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In a human-AI collaboration, users build a mental model of the AI systembased on its reliability and how it presents its decision, e.g. itspresentation of system confidence and an explanation of the output. Modern NLPsystems are often uncalibrated, resulting in confidently incorrect predictionsthat undermine user trust. In order to build trustworthy AI, we must understandhow user trust is developed and how it can be regained after potentialtrust-eroding events. We study the evolution of user trust in response to thesetrust-eroding events using a betting game. We find that even a few incorrectinstances with inaccurate confidence estimates damage user trust andperformance, with very slow recovery. We also show that this degradation intrust reduces the success of human-AI collaboration and that different types ofmiscalibration -- unconfidently correct and confidently incorrect -- havedifferent negative effects on user trust. Our findings highlight the importanceof calibration in user-facing AI applications and shed light on what aspectshelp users decide whether to trust the AI system.

A Diachronic Perspective on User Trust in AI under Uncertainty