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

With their increasing size, large language models (LLMs) are becomingincreasingly good at language understanding tasks. But even with highperformance on specific downstream task, LLMs fail at simple linguistic testsfor negation or quantifier understanding. Previous work on quantifierunderstanding in LLMs show inverse scaling in understanding few-typequantifiers. In this paper, we question the claims of of previous work and showthat it is a result of inappropriate testing methodology. We also presentalternate methods to measure quantifier comprehension in LLMs and show thatLLMs are able to better understand the difference between the meaning offew-type and most-type quantifiers as their size increases, although they arenot particularly good at it. We also observe inverse scaling for most-typequantifier understanding, which is contrary to human psycho-linguisticexperiments and previous work, where the model's understanding of most-typequantifier gets worse as the model size increases. We do this evaluation onmodels ranging from 125M-175B parameters, which suggests that LLMs do not do aswell as expected with quantifiers. We also discuss the possible reasons forthis and the relevance of quantifier understanding in evaluating languageunderstanding in LLMs.

Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling