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 evaluation of the fidelity of eXplainable Artificial Intelligence (XAI)methods to their underlying models is a challenging task, primarily due to theabsence of a ground truth for explanations. However, assessing fidelity is anecessary step for ensuring a correct XAI methodology. In this study, weconduct a fair and objective comparison of the current state-of-the-art XAImethods by introducing three novel image datasets with reliable ground truthfor explanations. The primary objective of this comparison is to identifymethods with low fidelity and eliminate them from further research, therebypromoting the development of more trustworthy and effective XAI techniques. Ourresults demonstrate that XAI methods based on the backpropagation of outputinformation to input yield higher accuracy and reliability compared to methodsrelying on sensitivity analysis or Class Activation Maps (CAM). However, thebackpropagation method tends to generate more noisy saliency maps. Thesefindings have significant implications for the advancement of XAI methods,enabling the elimination of erroneous explanations and fostering thedevelopment of more robust and reliable XAI.

Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets