In an era where artificial intelligence (AI) has redefined technological boundaries, large language models like ChatGPT now generate outputs that simulate deeply human capacities, including empathy ...

Schematic overview of the study design. The authors asked large language models (LLMs) to rate approximately 700 English words that are typically acquired early in childhood according to 21 ...

To assess the similarity of model word ratings to human word ratings across each dimension, we calculated the Spearman rank correlation between model-generated and human-generated ratings at both the ...