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

How well do language models deal with quantification? In this study, we focuson 'few'-type quantifiers, as in 'few children like toys', which might pose aparticular challenge for language models because the sentence components without the quantifier are likely to co-occur, and 'few'-type quantifiers are rare.We present 960 English sentence stimuli from two human neurolinguisticexperiments to 22 autoregressive transformer models of differing sizes. Notonly do all the models perform poorly on 'few'-type quantifiers, but overallthe larger the model, the worse its performance. This inverse scaling isconsistent with previous work suggesting that larger models increasinglyreflect online rather than offline human processing, and we argue that thedecreasing performance of larger models may challenge uses of language modelsas the basis for natural language systems.

Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers