LLMs obviously aren't reproducing the internal cognitive process, but they might still capture some of the structural patterns that emerge from it
Interestingly, there is some neuroscience research that transformer architecture resembles "cue based retrieval" in the human brain in some important ways.
https://www.sciencedirect.com/science/article/pii/S0749596X2...
Interestingly, there is some neuroscience research that transformer architecture resembles "cue based retrieval" in the human brain in some important ways.
https://www.sciencedirect.com/science/article/pii/S0749596X2...