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

Large language models (LLMs), such as the General Pre-trained Transformer(GPT), have shown remarkable performance in various cognitive tasks. However,it remains unclear whether these models have the ability to accurately inferhuman perceptual representations. Previous research has addressed this questionby quantifying correlations between similarity response patterns from humansand LLMs. Although it has been shown that the correlation between humans andLLMs is reasonably high, simple correlation analysis is inadequate to revealthe degree of detailed structural correspondence between humans and LLMs. Here,we use an unsupervised alignment method based on Gromov-Wasserstein optimaltransport to assess the equivalence of similarity structures between humans andLLMs in a more detailed manner. As a tractable study, we compare the colorsimilarity structures of humans (color-neurotypical and color-atypicalparticipants) and two GPT models (GPT-3.5 and GPT-4) by examining thesimilarity structures of 93 colors. Our results show that the similaritystructures of color-neurotypical humans can be remarkably well-aligned to thatof GPT-4 and, to a lesser extent, to that of GPT-3.5. These results contributeto our understanding of the ability of LLMs to accurately infer humanperception, and highlight the potential of unsupervised alignment methods toreveal detailed structural equivalence or differences that cannot be detectedby simple correlation analysis.

Comparing Color Similarity Structures between Humans and LLMs via Unsupervised Alignment