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

The right to AI explainability has consolidated as a consensus in theresearch community and policy-making. However, a key component ofexplainability has been missing: extrapolation, which describes the extent towhich AI models can be clueless when they encounter unfamiliar samples (i.e.,samples outside the convex hull of their training sets, as we will explain). Wereport that AI models extrapolate outside their range of familiar data,frequently and without notifying the users and stakeholders. Knowing whether amodel has extrapolated or not is a fundamental insight that should be includedin explaining AI models in favor of transparency and accountability. Instead ofdwelling on the negatives, we offer ways to clear the roadblocks in promotingAI transparency. Our analysis commentary accompanying practical clauses usefulto include in AI regulations such as the National AI Initiative Act in the USand the AI Act by the European Commission.

Should Machine Learning Models Report to Us When They Are Clueless?