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

There is an increasing consensus about the effectiveness of user-centredapproaches in the explainable artificial intelligence (XAI) field. Indeed, thenumber and complexity of personalised and user-centred approaches to XAI haverapidly grown in recent years. Often, these works have a two-fold objective:(1) proposing novel XAI techniques able to consider the users and (2) assessingthe \textit{goodness} of such techniques with respect to others. From these newworks, it emerged that user-centred approaches to XAI positively affect theinteraction between users and systems. However, so far, the goodness of XAIsystems has been measured through indirect measures, such as performance. Inthis paper, we propose an assessment task to objectively and quantitativelymeasure the goodness of XAI systems in terms of their \textit{informationpower}, which we intended as the amount of information the system provides tothe users during the interaction. Moreover, we plan to use our task toobjectively compare two XAI techniques in a human-robot decision-making task tounderstand deeper whether user-centred approaches are more informative thanclassical ones.

How much informative is your XAI? A decision-making assessment task to objectively measure the goodness of explanations