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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In their seminal article on semantic vectors, Landauer and Dumain (1997)proposed testing the quality of AI language models with a challengingvocabulary test. We show that their Test of English as a Foreign Language(TOEFL) test remains informative for contemporary major language models, sincenone of the models was perfect and made errors on divergent items. The TOEFLtest consists of target words with four alternatives to choose from. We furthertested the models on a Yes/No test that requires distinguishing betweenexisting words and made-up nonwords. The models performed significantly worseon the nonword items, in line with other observations that current majorlanguage models provide non-existent information. The situation was worse whenwe generalized the tests to Spanish. Here, most models gavemeanings/translations for the majority of random letter sequences. On the plusside, the best models began to perform quite well, and they also pointed tononwords that were unknown to the test participants but can be found indictionaries.

The continued usefulness of vocabulary tests for evaluating large language models