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

Interpretable Machine Learning (IML) has become increasingly important inmany real-world applications, such as autonomous cars and medical diagnosis,where explanations are significantly preferred to help people better understandhow machine learning systems work and further enhance their trust towardssystems. However, due to the diversified scenarios and subjective nature ofexplanations, we rarely have the ground truth for benchmark evaluation in IMLon the quality of generated explanations. Having a sense of explanation qualitynot only matters for assessing system boundaries, but also helps to realize thetrue benefits to human users in practical settings. To benchmark the evaluationin IML, in this article, we rigorously define the problem of evaluatingexplanations, and systematically review the existing efforts fromstate-of-the-arts. Specifically, we summarize three general aspects ofexplanation (i.e., generalizability, fidelity and persuasibility) with formaldefinitions, and respectively review the representative methodologies for eachof them under different tasks. Further, a unified evaluation framework isdesigned according to the hierarchical needs from developers and end-users,which could be easily adopted for different scenarios in practice. In the end,open problems are discussed, and several limitations of current evaluationtechniques are raised for future explorations.

Evaluating Explanation Without Ground Truth in Interpretable Machine Learning