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

Referenceless metrics (e.g., CLIPScore) use pretrained vision--languagemodels to assess image descriptions directly without costly ground-truthreference texts. Such methods can facilitate rapid progress, but only if theytruly align with human preference judgments. In this paper, we introduceContextRef, a benchmark for assessing referenceless metrics for such alignment.ContextRef has two components: human ratings along a variety of establishedquality dimensions, and ten diverse robustness checks designed to uncoverfundamental weaknesses. A crucial aspect of ContextRef is that images anddescriptions are presented in context, reflecting prior work showing thatcontext is important for description quality. Using ContextRef, we assess avariety of pretrained models, scoring functions, and techniques forincorporating context. None of the methods is successful with ContextRef, butwe show that careful fine-tuning yields substantial improvements. ContextRefremains a challenging benchmark though, in large part due to the challenge ofcontext dependence.

ContextRef: Evaluating Referenceless Metrics For Image Description Generation