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

Knowledge graphs (KGs) have helped neural models improve performance onvarious knowledge-intensive tasks, like question answering and itemrecommendation. By using attention over the KG, such KG-augmented models canalso "explain" which KG information was most relevant for making a givenprediction. In this paper, we question whether these models are really behavingas we expect. We show that, through a reinforcement learning policy (or evensimple heuristics), one can produce deceptively perturbed KGs, which maintainthe downstream performance of the original KG while significantly deviatingfrom the original KG's semantics and structure. Our findings raise doubts aboutKG-augmented models' ability to reason about KG information and give sensibleexplanations.

Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation