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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Ante-hoc interpretability has become the holy grail of explainable artificialintelligence for high-stakes domains such as healthcare; however, this notionis elusive, lacks a widely-accepted definition and depends on the operationalcontext. It can refer to predictive models whose structure adheres todomain-specific constraints, or ones that are inherently transparent. Thelatter conceptualisation assumes observers who judge this quality, whereas theformer presupposes them to have technical and domain expertise (thus alienatingother groups of explainees). Additionally, the distinction between ante-hocinterpretability and the less desirable post-hoc explainability, which refersto methods that construct a separate explanatory model, is vague given thattransparent predictive models may still require (post-)processing to yieldsuitable explanatory insights. Ante-hoc interpretability is thus an overloadedconcept that comprises a range of implicit properties, which we unpack in thispaper to better understand what is needed for its safe adoption acrosshigh-stakes domains. To this end, we outline modelling and explainingdesiderata that allow us to navigate its distinct realisations in view of theenvisaged application and audience.

(Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility