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

Post hoc explanations have emerged as a way to improve user trust in machinelearning models by providing insight into model decision-making. However,explanations tend to be evaluated based on their alignment with prior knowledgewhile the faithfulness of an explanation with respect to the model, afundamental criterion, is often overlooked. Furthermore, the effect ofexplanation faithfulness and alignment on user trust and whether this effectdiffers among laypeople and domain experts is unclear. To investigate thesequestions, we conduct a user study with computer science students and doctorsin three domain areas, controlling the laypeople and domain expert groups ineach setting. The results indicate that laypeople base their trust inexplanations on explanation faithfulness while domain experts base theirs onexplanation alignment. To our knowledge, this work is the first to show that(1) different factors affect laypeople and domain experts' trust in post hocexplanations and (2) domain experts are subject to specific biases due to theirexpertise when interpreting post hoc explanations. By uncovering thisphenomenon and exposing this cognitive bias, this work motivates the need toeducate end users about how to properly interpret explanations and overcometheir own cognitive biases, and motivates the development of simple andinterpretable faithfulness metrics for end users. This research is particularlyimportant and timely as post hoc explanations are increasingly being used inhigh-stakes, real-world settings such as medicine.

Is Ignorance Bliss? The Role of Post Hoc Explanation Faithfulness and Alignment in Model Trust in Laypeople and Domain Experts