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/

Zendy Plus

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

Zendy Tools

Zendy Open

Large Language Models (LLMs) are recruited in applications that span fromclinical assistance and legal support to question answering and education.Their success in specialized tasks has led to the claim that they possesshuman-like linguistic capabilities related to compositional understanding andreasoning. Yet, reverse-engineering is bound by Moravec's Paradox, according towhich easy skills are hard. We systematically assess 7 state-of-the-art modelson a novel benchmark. Models answered a series of comprehension questions, eachprompted multiple times in two settings, permitting one-word or open-lengthreplies. Each question targets a short text featuring high-frequency linguisticconstructions. To establish a baseline for achieving human-like performance, wetested 400 humans on the same prompts. Based on a dataset of n=26,680datapoints, we discovered that LLMs perform at chance accuracy and waverconsiderably in their answers. Quantitatively, the tested models areoutperformed by humans, and qualitatively their answers showcase distinctlynon-human errors in language understanding. We interpret this evidence assuggesting that, despite their usefulness in various tasks, current AI modelsfall short of understanding language in a way that matches humans, and we arguethat this may be due to their lack of a compositional operator for regulatinggrammatical and semantic information.

Testing AI on language comprehension tasks reveals insensitivity to underlying meaning