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

Visual inspection tasks often require humans to cooperate with AI-based imageclassifiers. To enhance this cooperation, explainable artificial intelligence(XAI) can highlight those image areas that have contributed to an AI decision.However, the literature on visual cueing suggests that such XAI support mightcome with costs of its own. To better understand how the benefits and cost ofXAI depend on the accuracy of AI classifications and XAI highlights, weconducted two experiments that simulated visual quality control in a chocolatefactory. Participants had to decide whether chocolate moulds contained faultybars or not, and were always informed whether the AI had classified the mouldas faulty or not. In half of the experiment, they saw additional XAI highlightsthat justified this classification. While XAI speeded up performance, itseffects on error rates were highly dependent on (X)AI accuracy. XAI benefitswere observed when the system correctly detected and highlighted the fault, butXAI costs were evident for misplaced highlights that marked an intact areawhile the actual fault was located elsewhere. Eye movement analyses indicatedthat participants spent less time searching the rest of the mould and thuslooked at the fault less often. However, we also observed large interindividualdifferences. Taken together, the results suggest that despite its potentials,XAI can discourage people from investing effort into their own informationanalysis.

The benefits and costs of explainable artificial intelligence in visual quality control: Evidence from fault detection performance and eye movements