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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Counterfactual explanations (CFEs) highlight what changes to a model's inputwould have changed its prediction in a particular way. CFEs have gainedconsiderable traction as a psychologically grounded solution for explainableartificial intelligence (XAI). Recent innovations introduce the notion ofcomputational plausibility for automatically generated CFEs, enhancing theirrobustness by exclusively creating plausible explanations. However, practicalbenefits of such a constraint on user experience and behavior is yet unclear.In this study, we evaluate objective and subjective usability ofcomputationally plausible CFEs in an iterative learning design targeting noviceusers. We rely on a novel, game-like experimental design, revolving around anabstract scenario. Our results show that novice users actually benefit lessfrom receiving computationally plausible rather than closest CFEs that produceminimal changes leading to the desired outcome. Responses in a post-game surveyreveal no differences in terms of subjective user experience between bothgroups. Following the view of psychological plausibility as comparativesimilarity, this may be explained by the fact that users in the closestcondition experience their CFEs as more psychologically plausible than thecomputationally plausible counterpart. In sum, our work highlights alittle-considered divergence of definitions of computational plausibility andpsychological plausibility, critically confirming the need to incorporate humanbehavior, preferences and mental models already at the design stages of XAIapproaches. In the interest of reproducible research, all source code, acquireduser data, and evaluation scripts of the current study are available:https://github.com/ukuhl/PlausibleAlienZoo

2022 acm conference on fairness, accountability, and transparency

Keep Your Friends Close and Your Counterfactuals Closer: Improved  Learning From Closest Rather Than Plausible Counterfactual Explanations in an  Abstract Setting