In a study published last month https://www.nature.com/articles/s41562-025-02297-0 [nature.com] researchers analyze internal sentence representation for both humans and LLMs. It turns out that humans and LLMs use similar tree structures. Quote from their conclusions: " The results also add to the literature showing that the human brain and LLM, albeit fundamentally different in terms of the implementation, can have aligned internal representations of language."
Originally seen on techxplore https://techxplore.com/news/2025-10-humans-llms-sentences-similarly.html [techxplore.com]